800 篇顶会论文纵览推荐系统的前沿进展

机构｜中国人民大学高瓴人工智能学院

引言：推荐系统作为人工智能领域最具有应用前景的方向之一，在学术界和工业界一直占据着重要地位。本文聚焦于推荐系统在学术研究方面的前沿进展，在之前整理的 Awesome-RSPapers 基础上扩展了近两年顶会中推荐系统相关的论文，涵盖 SIGIR、SIGKDD、RecSys、CIKM、AAAI、WSDM、WWW 的 20 次会议。本次整理以长文和研究性论文为主，也包含部分短文和工业论文。由于工作量巨大，难免有疏漏，欢迎大家在评论区指正。

本次整理的论文结合了之前文章的内容：从200多篇顶会论文看推荐系统前沿方向与最新进展，新增的论文已同步更新至 GitHub。Awesome-RSPapers 会持续更新推荐系统的顶会论文，并分别按照任务、话题和技术进行分类；Top-conference-paper-list 收集了自然语言处理、推荐系统和其他相关领域的顶级会议论文。欢迎大家关注和 Star~

推荐系统论文：

RUCAIBox/Awesome-RSPapersgithub.com/RUCAIBox/Awesome-RSPapers

顶会论文整理：

RUCAIBox/Top-conference-paper-listgithub.com/RUCAIBox/Top-conference-paper-list

(11次)：SIGIR 2020, SIGKDD 2020, RecSys 2020, CIKM 2020, AAAI 2021, WSDM 2021, WWW 2021, SIGIR 2021, SIGIR 2022, ACL 2022, NeurIPS 2022
本次新增的会议 (11次)：RecSys 2021, KDD 2021, RecSys 2022, KDD 2022, AAAI 2022, CIKM 2021, CIKM 2022, WSDM 2022, WWW 2022, NIPS 2022, IJCAI 2022

同时欢迎大家使用 RecBole（伯乐）推荐系统工具包，在 GitHub 上已经有 2.1k 个 star 和 400 个 fork。RecBole 是一个基于 PyTorch 实现的，面向研究者的，易于开发与复现的，统一、全面、高效的推荐系统代码库。目前已经有 83 个常见的推荐模型，覆盖主流的研究任务，支持全面多样的数据处理与评测方式。同时我们也整理了 41 个常用的推荐系统数据集，可以直接在 RecBole 中使用。

此外，RecBole2.0 在伯乐框架的基础上推出 8 个最新扩展包，覆盖从数据到模型多个推荐系统最新的主题和方向，为推荐系统多个领域的研究提供了易用又强大的工具库！欢迎大家关注我们小组的推荐算法开源工作～

RUCAIBox/RecBolegithub.com/RUCAIBox/RecBole

RUCAIBox/RecBole2.0github.com/RUCAIBox/RecBole2.0

RUCAIBox/RecSysDatasetsgithub.com/RUCAIBox/RecSysDatasets

本文根据文章的侧重点将这些论文分为以下三大类和若干小类：

按任务划分
- 协同过滤 (Collaborative Filtering)
- 序列推荐 (Sequential/Session-based Recommendation)
- 点击率预测 (CTR/CVR Prediction)
- 知识感知的推荐 (Knowledge-aware Recommendation)
- 对话推荐系统 (Conversational Recommender System)
- 社交推荐 (Social Recommendation)
- 新闻推荐 (News Recommendation)
- 音乐推荐 (Music Recommendation)
- 文本感知的推荐 (Text-aware Recommendation)
- 兴趣点推荐 (POI Recommendation)
- 在线推荐 (Online Recommendation)
- 组推荐 (Group Recommendation)
- 多任务/多行为/跨域推荐 (Multi-task/Multi-behavior/Cross-domain Recommendation)
- 多模态推荐 (Multimodal Recommendation)
- 其他任务 (Other Tasks)

按话题划分
- 推荐系统去偏 (Debias in Recommender System)
- 推荐系统公平性 (Fairness in Recommender System)
- 推荐系统中的攻击 (Attack in Recommender System)
- 推荐系统可解释性 (Explanation in Recommender System)
- 推荐系统的长尾/冷启动问题 (Long-tail/Cold-start in Recommendation)
- 推荐系统多样性 (Diversity in Recommendation)
- 推荐系统去噪 (Denoising in Recommendation)
- 推荐的隐私保护 (Privacy Protection in Recommendation)
- 推荐系统的评价和实验分析 (Evaluation of Recommender System)
- 其他话题 (Other Topics)

按技术划分
- 推荐系统预训练 (Pre-training in Recommender System)
- 推荐中的强化学习 (Reinforcement Learning in Recommendation)
- 推荐中的知识蒸馏 (Knowledge Distillation in Recommendation)
- 推荐中的联邦学习 (Federated Learning in Recommendation)
- 推荐中的图神经网络 (GNN in Recommendation)
- 基于对比学习的推荐 (Contrastive Learning based Recommendation)
- 基于对抗学习的推荐 (Adversarial Learning based Recommendation)
- 基于自动编码器的推荐 (Autoencoder based Recommendation)
- 基于元学习的推荐 (Meta Learning-based Recommendation)
- 基于自动机器学习的推荐 (AutoML-based Recommendation)
- 基于因果推断的推荐 (Casual Inference/Counterfactual)
- 其他技术 (Other Techniques)

1. 按任务划分

协同过滤 (Collaborative Filtering)

作为推荐系统最经典的算法之一，协同过滤通过挖掘用户和物品的交互信息，将相似的物品推荐给类似的用户。从早期基于用户或物品邻域的 UserKNN 和 ItemKNN 方法，到基于矩阵分解的 SVD++、BPRMF，再到近几年基于图神经网络的 NGCF、LightGCN 等模型，基于相似性进行推荐的思路时至今日仍然在新技术的推动下焕发着强大的生机。最新的针对协同过滤的研究依然在探索如何捕获交互中的相似性信息，包括建模更高阶的交互，设计更复杂的度量空间等。

SimpleX: A Simple and Strong Baseline for Collaborative Filtering. CIKM 2021【将Cosine Contrastive Loss引入协同过滤】
Incremental Graph Convolutional Network for Collaborative Filtering. CIKM 2021【增量图卷积神经网络用于协同过滤】
LT-OCF: Learnable-Time ODE-based Collaborative Filtering. CIKM 2021【Learnable-Time CF】
CausCF: Causal Collaborative Filtering for Recommendation Effect Estimation. CIKM 2021【applied paper，因果关系协同过滤用于推荐效果评估】
Vector-Quantized Autoencoder With Copula for Collaborative Filtering. CIKM 2021【short paper，用于协同过滤的矢量量化自动编码器】
Anchor-based Collaborative Filtering for Recommender Systems. CIKM 2021【short paper，Anchor-based推荐系统协同过滤】
XPL-CF: Explainable Embeddings for Feature-based Collaborative Filtering. CIKM 2021【short paper，可解释 Embedding 用于基于特征的协同过滤】
NMO: A Model-Agnostic and Scalable Module for Inductive Collaborative Filtering. SIGIR 2022 【模型无关的归纳式协同过滤模块】
Collaborative Filtering with Attribution Alignment for Review-based Non-overlapped Cross Domain Recommendation. WWW 2022 【通过属性对齐实现基于评论的跨域推荐】
Neuro-Symbolic Interpretable Collaborative Filtering for Attribute-based Recommendation. WWW 2022 【以模型为核心的神经符号可解释协同过滤】
Improving Graph Collaborative Filtering with Neighborhood-enriched Contrastive Learning. WWW 2022 【通过邻居节点间的对比学习来改善图协同过滤】
Hypercomplex Graph Collaborative Filtering. WWW 2022 【超复图协同过滤】
Improving Graph Collaborative Filtering with Neighborhood-enriched Contrastive Learning. WWW 2022 【通过邻居节点间的对比学习来改善图协同过滤】
On Sampling Collaborative Filtering Datasets. WSDM 2022【关于采样协同过滤数据集】
Profiling the Design Space for Graph Neural Networks based Collaborative Filtering. WSDM 2022【分析基于图神经网络的协同过滤的设计空间】
VAE++: Variational AutoEncoder for Heterogeneous One-Class Collaborative Filtering. WSDM 2022【异构单类协同过滤的变分自动编码器】
Geometric Inductive Matrix Completion: A Hyperbolic Approach with Unified Message Passing. WSDM 2022 【具有统一消息传递的双曲线方法】
Asymmetrical Context-aware Modulation for Collaborative Filtering Recommendation. CIKM 2022 【用于协同过滤推荐的非对称上下文感知调制】
Dynamic Causal Collaborative Filtering. CIKM 2022 【动态因果协同过滤】
Towards Representation Alignment and Uniformity in Collaborative Filtering. KDD 2022 【用户和物品表示对齐】
HICF: Hyperbolic Informative Collaborative Filtering. KDD 2022 【双曲空间增强表示】
Geometric Disentangled Collaborative Filtering. SIGIR 2022 【几何解耦的协同过滤】
Learning to Denoise Unreliable Interactions for Graph Collaborative Filtering. SIGIR 2022 【数据去噪】
Self-Augmented Recommendation with Hypergraph Contrastive Collaborative Filtering. SIGIR 2022 【超图上的对比学习】
Investigating Accuracy-Novelty Performance for Graph-based Collaborative Filtering. SIGIR 2022 【图协同过滤在准确度和新颖度上的表现】
Unify Local and Global Information for Top-N Recommendation. SIGIR 2022 【综合局部和全局信息】
Enhancing Top-N Item Recommendations by Peer Collaboration. SIGIR 2022 【short paper ，同龄人协同】
Evaluation of Herd Behavior Caused by Population-scale Concept Drift in Collaborative Filtering. SIGIR 2022 【short paper】
Matrix Factorization for Collaborative Filtering Is Just Solving an Adjoint Latent Dirichlet Allocation Model After All. RecSys 2021【矩阵分解式协同过滤的理论联系】
Negative Interactions for Improved Collaborative-Filtering: Don’t go Deeper, go Higher. RecSys 2021【线性全秩模型考虑高阶交互的扩展】
Privacy Preserving Collaborative Filtering by Distributed Mediation. RecSys 2021【隐私保护式协同过滤】
ProtoCF: Prototypical Collaborative Filtering for Few-shot Item Recommendation. RecSys 2021【少样本物品推荐的原型协同过滤】
Reenvisioning the comparison between Neural Collaborative Filtering and Matrix Factorization. RecSys 2021 【Reproducibility paper，神经协同过滤与矩阵分解的比较】
Investigating Overparameterization for Non-Negative Matrix Factorization in Collaborative Filtering. RecSys 2021【LBR，协同过滤中非负矩阵分解的过参数化研究】
ProtoMF: Prototype-based Matrix Factorization for Effective and Explainable Recommendations. RecSys 2022【基于原型的可解释协同过滤算法】
Revisiting the Performance of iALS on Item Recommendation Benchmarks. RecSys 2022【Reproducibility paper，隐式交替最小二乘法 iALS 基准表现的再思考】
Scalable Linear Shallow Autoencoder for Collaborative Filtering. RecSys 2022 【LBR，用于协同过滤的可扩展线性浅层自动编码器】
HCFRec: Hash Collaborative Filtering via Normalized Flow with Structural Consensus for Efficient Recommendation. IJCAI 2022 【为 hash-CF 学习最优哈希码】
Trading Hard Negatives and True Negatives: A Debiased Contrastive Collaborative Filtering Approach. IJCAI 2022 【探索正确的负样本】

Sequential/Session-based Recommendations

序列推荐也是十分热门的研究方向。通过建模用户的历史交互序列来刻画用户偏好。从早期的基于Markov Chain来建模。到基于序列模型建模，如GRU,Transformer等。随着图神经网络的不断发展，也就不少基于GNN的序列推荐方法被提出。一些工作也开始尝试将预训练引入序列推荐中，建模更通用的用户、商品、序列表征。

Seq2Bubbles: Region-Based Embedding Learning for User Behaviors in Sequential Recommenders. CIKM 2021【序列推荐中基于区域的用户行为Embedding学习】
Enhancing User Interest Modeling with Knowledge-Enriched Itemsets for Sequential Recommendation. CIKM 2021【序列推荐中使用物品集增强用户兴趣建模】
Continuous-Time Sequential Recommendation with Temporal Graph Collaborative Transformer. CIKM 2021【将时序图协同Transformer用于连续时间序列推荐】
Extracting Attentive Social Temporal Excitation for Sequential Recommendation. CIKM 2021【提取时序激励用于序列推荐】
Hyperbolic Hypergraphs for Sequential Recommendation. CIKM 2021【使用双曲超图进行序列推荐】
Learning Dual Dynamic Representations on Time-Sliced User-Item Interaction Graphs for Sequential Recommendation. CIKM 2021【用于序列推荐的在时间片用户物品交互图上的对偶动态表示】
Lightweight Self-Attentive Sequential Recommendation. CIKM 2021【使用CNN捕获局部特征，使用Self-Attention捕获全局特征】
What is Next when Sequential Prediction Meets Implicitly Hard Interaction? CIKM 2021【序列预测与交互】
Modeling Sequences as Distributions with Uncertainty for Sequential Recommendation. CIKM 2021【short paper，序列建模】
Locker: Locally Constrained Self-Attentive Sequential Recommendation. CIKM 2021【short paper，局部约束的自注意力序列推荐】
CBML: A Cluster-based Meta-learning Model for Session-based Recommendation. CIKM 2021【用于会话推荐的基于聚类的元学习】
Self-Supervised Graph Co-Training for Session-based Recommendation. CIKM 2021【用于会话推荐的自监督图协同训练】
S-Walk: Accurate and Scalable Session-based Recommendation with Random Walks. WSDM 2022【具有随机游走的准确且可扩展的基于会话的推荐】
Learning Multi-granularity Consecutive User Intent Unit for Session-based Recommendation. WSDM 2022【基于会话的推荐学习多粒度连续用户意图单元】
A Relevant and Diverse Retrieval-enhanced Data Augmentation Framework for Sequential Recommendation. CIKM 2022 【Applied Research Track, 用于顺序推荐的相关且多样化的检索增强数据增强框架】
Beyond Learning from Next Item: Sequential Recommendation via Personalized Interest Sustainability. CIKM 2022 【基于个性化兴趣可持续性的序列推荐】
Storage-saving Transformer for Sequential Recommendations. CIKM 2022 【用于序列推荐的节省存储的Transformer】
Contrastive Learning with Bidirectional Transformers for Sequential Recommendation. CIKM 2022 【用于序列推荐的双向 Transformer 对比学习】
FwSeqBlock: A Field-wise Approach for Modeling Behavior Representation in Sequential Recommendation. CIKM 2022 【建模行为表示】
Dually Enhanced Propensity Score Estimation in Sequential Recommendation. CIKM 2022 【双重增强倾向得分估计】
Hierarchical Item Inconsistency Signal learning for Sequence Denoising in Sequential Recommendation. CIKM 2022 【序列推荐中序列去噪的分层项目不一致信号学习】
ContrastVAE: Contrastive Variational AutoEncoder for Sequential Recommendation. CIKM 2022 【用于序列推荐的对比变分自动编码器】
Disentangling Past-Future Modeling in Sequential Recommendation via Dual Networks. CIKM 2022 【通过双网络解耦序列推荐中的过去未来】
Evolutionary Preference Learning via Graph Nested GRU ODE for Session-based Recommendation. CIKM 2022 【通过图嵌套 GRU ODE 进行进化偏好学习】
Spatiotemporal-aware Session-based Recommendation with Graph Neural Networks. CIKM 2022 【使用图神经网络的时空感知基于会话的推荐】
Time Lag Aware Sequential Recommendation. CIKM 2022 【延时感知序列推荐】
Temporal Contrastive Pre-Training for Sequential Recommendation. CIKM 2022 【时序推荐的时间对比预训练】
Debiasing the Cloze Task in Sequential Recommendation with Bidirectional Transformers. KDD 2022 【序列完形填空去偏】
PARSRec: Explainable Personalized Attention-fused Recurrent Sequential Recommendation Using Session Partial Actions. KDD 2022 【用户个性化区分】
Multi-Behavior Hypergraph-Enhanced Transformer for Sequential Recommendation. KDD 2022 【多行为超图增强】
NxtPost: User To Post Recommendations In Facebook Groups. KDD 2022 【引入外部token扩充预料】
Recommendation in Offline Stores: A Gamification Approach for Learning the Spatiotemporal Representation of Indoor Shopping. KDD 2022 【游戏化方法时空表征】
DiPS: Differentiable Policy for Sketching in Recommender Systems. AAAI 2022 【可微分的草图策略】
FPAdaMetric: False-Positive-Aware Adaptive Metric Learning for Session-Based Recommendation. AAAI 2022 【度量学习正则化】
SEMI: A Sequential Multi-Modal Information Transfer Network for E-Commerce Micro-Video Recommendations. KDD 2021 【基于序列多模态信息传输网络的电商微视频推荐系统】
Decoupled Side Information Fusion for Sequential Recommendation. SIGIR 2022 【融合边缘特征的序列推荐】
On-Device Next-Item Recommendation with Self-Supervised Knowledge Distillation. SIGIR 2022 【自监督知识蒸馏】
Multi-Agent RL-based Information Selection Model for Sequential Recommendation. SIGIR 2022 【多智能体信息选择】
An Attribute-Driven Mirroring Graph Network for Session-based Recommendation. SIGIR 2022 【特征驱动的反射图网络】
When Multi-Level Meets Multi-Interest: A Multi-Grained Neural Model for Sequential Recommendation. SIGIR 2022 【多粒度网络】
Price DOES Matter! Modeling Price and Interest Preferences in Session-based Recommendation. SIGIR 2022 【考虑价格和兴趣的推荐】
AutoGSR: Neural Architecture Search for Graph-based Session Recommendation. SIGIR 2022 【面向图会话推荐的网络结构搜索】
Ada-Ranker: A Data Distribution Adaptive Ranking Paradigm for Sequential Recommendation. SIGIR 2022 【数据分布自适应排序】
Multi-Faceted Global Item Relation Learning for Session-Based Recommendation. SIGIR 2022 【多面全局商品关系学习】
ReCANet: A Repeat Consumption-Aware Neural Network for Next Basket Recommendation in Grocery Shopping. SIGIR 2022 【考虑重复消费的网络】
Determinantal Point Process Set Likelihood-Based Loss Functions for Sequential Recommendation. SIGIR 2022 【基于DPP的损失函数】
Positive, Negative and Neutral: Modeling Implicit Feedback in Session-based News Recommendation. SIGIR 2022 【建模隐式反馈】
Coarse-to-Fine Sparse Sequential Recommendation. SIGIR 2022 【short paper，粗到细的稀疏序列化推荐】
Dual Contrastive Network for Sequential Recommendation. SIGIR 2022 【short paper，双对比网络】
Explainable Session-based Recommendation with Meta-Path Guided Instances and Self-Attention Mechanism. SIGIR 2022 【short paper，基于元路径指导和自注意力机制的可解释会话推荐】
Item-Provider Co-learning for Sequential Recommendation. SIGIR 2022 【short paper，商品-商家一同训练】
RESETBERT4Rec: A Pre-training Model Integrating Time And User Historical Behavior for Sequential Recommendation. SIGIR 2022 【short paper，融合时间和用户历史行为的预训练模型】
Enhancing Hypergraph Neural Networks with Intent Disentanglement for Session-based Recommendation. SIGIR 2022 【short paper，意图解耦增强超图神经网络】
CORE: Simple and Effective Session-based Recommendation within Consistent Representation Space. SIGIR 2022 【short paper，在一致表示空间上的简单有效会话推荐】
DAGNN: Demand-aware Graph Neural Networks for Session-based Recommendation. SIGIR 2022 【short paper，需求感知的图神经网络】
Progressive Self-Attention Network with Unsymmetrical Positional Encoding for Sequential Recommendation. SIGIR 2022 【short paper，使用非对称位置编码的自注意力网络】
ELECRec: Training Sequential Recommenders as Discriminators. SIGIR 2022 【short paper，训练序列推荐模型作为判别器】
Exploiting Session Information in BERT-based Session-aware Sequential Recommendation. SIGIR 2022 【short paper，在基于BERT的模型中利用会话信息】
Black-Box Attacks on Sequential Recommenders via Data-Free Model Extraction. RecSys 2021 【序列推荐的黑盒攻击】
Next-item Recommendations in Short Sessions. RecSys 2021 【短会话中的下一个物品推荐】
Transformers4Rec: Bridging the Gap between NLP and Sequential / Session-Based Recommendation. RecSys 2021 【建立自然语言处理和序列推荐的联系】
A Case Study on Sampling Strategies for Evaluating Neural Sequential Item Recommendation Models. RecSys 2021 【Reproducibility paper，序列推荐模型评测策略的研究】
Sequence Adaptation via Reinforcement Learning in Recommender Systems. RecSys 2021 【LBR，用强化学习方法进行序列推荐】
Aspect Re-distribution for Learning Better Item Embeddings in Sequential Recommendation. RecSys 2022 【序列推荐中物品向量的方面重分布】
Context and Attribute-Aware Sequential Recommendation via Cross-Attention. RecSys 2022 【交叉注意力机制实现上下文和属性感知的序列推荐】
Defending Substitution-Based Profile Pollution Attacks on Sequential Recommenders. RecSys 2022 【序列推荐中基于替代的对抗性攻击算法】
Denoising Self-Attentive Sequential Recommendation. RecSys 2022 【基于 Transformer 的序列推荐中自注意力机制的去噪】
Don't recommend the obvious: estimate probability ratios. RecSys 2022 【通过拟合逐点的互信息来改进序列推荐的流行度采样指标】
Effective and Efficient Training for Sequential Recommendation using Recency Sampling. RecSys 2022 【基于接近度采样进行高效的序列推荐】
Global and Personalized Graphs for Heterogeneous Sequential Recommendation by Learning Behavior Transitions and User Intentions. RecSys 2022 【异构序列推荐中通过全局和个性化的图建模学习行为转换和用户意图】
Learning Recommendations from User Actions in the Item-poor Insurance Domain. RecSys 2022 【保险领域使用循环神经网络的跨会话模型】
A Systematic Review and Replicability Study of BERT4Rec for Sequential Recommendation. RecSys 2022【Reproducibility paper，BERT4Rec 结果的系统回顾与可复现性研究】
Streaming Session-Based Recommendation: When Graph Neural Networks meet the Neighborhood. RecSys 2022【Reproducibility paper，图神经网络解决流会话推荐问题】
Learning to Ride a Buy-Cycle: A Hyper-Convolutional Model for Next Basket Repurchase Recommendation. RecSys 2022 【针对下一篮回购推荐问题的超卷积模型】
M2TRec: Metadata-aware Multi-task Transformer for Large-scale and Cold-start free Session-based Recommendations. RecSys 2022【LBR，基于元数据和多任务 Transformer 的冷启动会话推荐系统】
MLP4Rec: A Pure MLP Architecture for Sequential Recommendations. IJCAI 2022 【利用MLP捕捉商品特征中的序列关系】
Enhancing Sequential Recommendation with Graph Contrastive Learning. IJCAI 2022 【用于序列推荐的图对比学习】
Disentangling Long and Short-Term Interests for Recommendation. WWW 2022 【利用自监督对比学习解耦长短期兴趣】
Efficient Online Learning to Rank for Sequential Music Recommendation. WWW 2022 【将搜索空间限制在此前表现不佳的搜索方向的正交补上】
Filter-enhanced MLP is All You Need for Sequential Recommendation. www 2022 【通过可学习滤波器对用户序列进行编码】
Generative Session-based Recommendation. WWW 2022 【构建生成器来模拟用户序列行为，从而改善目标序列推荐模型】
GSL4Rec: Session-based Recommendations with Collective Graph Structure Learning and Next Interaction Prediction. WWW 2022 【图结构学习+推荐】
Intent Contrastive Learning for Sequential Recommendation. WWW 2022 【利用用户意图来增强序列推荐】
Learn from Past, Evolve for Future: Search-based Time-aware Recommendation with Sequential Behavior Data. WWW 2022 【检索相关历史行为并融合当前序列行为】
Sequential Recommendation via Stochastic Self-Attention. WWW 2022 【通过随机高斯分布和Wasserstein自注意力模块来引入不确定性】
Sequential Recommendation with Decomposed Item Feature Routing. WWW 2022 【解耦item特征，并分别利用软硬模型来路由最有特征序列】
Towards Automatic Discovering of Deep Hybrid Network Architecture for Sequential Recommendation. WWW 2022 【通过NAS来搜索每一层使用注意力/卷积模块】
Unbiased Sequential Recommendation with Latent Confounders. WWW 2022 【去除潜在混淆变量来实现无偏序列推荐】
Re4: Learning to Re-contrast, Re-attend, Re-construct for Multi-interest Recommendation. WWW 2022 【通过re-contrast,re-attend,re-construct来增强解耦用户多兴趣表示】

CTR/CVR Prediction

这类工作旨在对用户是否点击展示的商品/广告做出二分类预测。近期研究热点包括高阶特征交互，设计高阶向量交互运算来构造显式的特征交互；图表示学习，异构特征图预训练增强特征表示；网络结构化搜索，采用强化学习或进化算法优化特征工程搜索最佳网络结构；多任务学习，通过点击率与转化率联合建模实现多个任务间互相增益。

Multi-task Learning for Bias-Free Joint CTR Prediction and Market Price Modeling in Online Advertising. CIKM 2021【在线广告无偏差联合CTR预估和市场价格建模的多任务学习】
Enhancing Explicit and Implicit Feature Interactions via Information Sharing for Parallel Deep CTR Models. CIKM 2021【applied paper，用于并行 CTR 的显式和隐式特征交互增强】
TSI: An Ad Text Strength Indicator using Text-to-CTR and Semantic-Ad-Similarity. CIKM 2021【applied paper，使用 Text-to-CTR 和 Semantic-Ad-Similarity 的广告文本强度指标】
One Model to Serve All: Star Topology Adaptive Recommender for Multi-Domain CTR Prediction. CIKM 2021【applied paper，用于多领域CTR预估的自适应推荐】
Efficient Learning to Learn a Robust CTR Model for Web-scale Online Sponsored Search Advertising. CIKM 2021【applied paper，用于在线搜索广告的CTR模型】
AutoIAS: Automatic Integrated Architecture Searcher for Click-Trough Rate Prediction. CIKM 2021【CTR预估的自动集成搜索架构】
Click-Through Rate Prediction with Multi-Modal Hypergraphs. CIKM 2021【使用多模态超图的点击率预测】
Open Benchmarking for Click-Through Rate Prediction. CIKM 2021【开源CTR预估Benchmark】
Disentangled Self-Attentive Neural Networks for Click-Through Rate Prediction. CIKM 2021【short paper，用于CTR预估的自注意力网络】
AutoHERI: Automated Hierarchical Representation Integration for Post-Click Conversion Rate Estimation. CIKM 2021【short paper，用于点击后转换率估计的分层表示学习】
Sequential Modeling with Multiple Attributes for Watchlist Recommendation in E-Commerce. WSDM 2022【电子商务中观察列表推荐的多属性序列建模】
Modeling Users’ Contextualized Page-wise Feedback for Click-Through Rate Prediction in E-commerce Search. WSDM 2022【电子商务搜索中点击率预测的用户情境化页面反馈建模】
Learning-To-Ensemble by Contextual Rank Aggregation in E-Commerce. WSDM 2022【通过电子商务中的上下文排名聚合学习集成】
CAN: Feature Co-Action Network for Click-Through Rate Prediction. WSDM 2022【用于点击率预测的特征协同网络】
Triangle Graph Interest Network for Click-through Rate Prediction. WSDM 2022【用于点击率预测的三角图兴趣网络】
OptEmbed: Learning Optimal Embedding Table for Click-through Rate Prediction. CIKM 2022 【点击率预测的最优嵌入表】
Multi-Interest Refinement by Collaborative Attributes Modeling for Click-Through Rate Prediction. CIKM 2022 【通过协作属性建模进行多兴趣细化的点击率预测】
GIFT: Graph-guIded Feature Transfer for Cold-Start Video Click-Through Rate Prediction. CIKM 2022 【GIFT：用于冷启动视频点击率预测的图引导特征迁移】
Graph Based Long-Term And Short-Term Interest Model for Click-Through Rate Prediction. CIKM 2022 【用于点击率预测的基于图的长期和短期兴趣模型】
Hierarchically Fusing Long and Short-Term User Interests for Click-Through Rate Prediction in Product Search. CIKM 2022 【分层融合长期和短期用户兴趣以进行产品搜索中的点击率预测】
Sparse Attentive Memory Network for Click-through Rate Prediction with Long Sequences. CIKM 2022 【用于长序列点击率预测的稀疏注意力记忆网络】
Towards Understanding the Overfitting Phenomenon of Deep Click-Through Rate Models. CIKM 2022 【了解深度点击率模型的过拟合现象】
User-Event Graph Embedding Learning for Context-Aware Recommendation. KDD 2022 【CTR 任务引入用户-事件图进行表示学习】
Adversarial Gradient Driven Exploration for Deep Click-Through Rate Prediction. KDD 2022 【CTR EE 探索】
Combo-Fashion: Fashion Clothes Matching CTR Prediction with Item History. KDD 2022 【流行服饰匹配增强 CTR】
Enhancing CTR Prediction with Context-Aware Feature Representation Learning. SIGIR 2022 【上下文相关的特征表示】
HIEN: Hierarchical Intention Embedding Network for Click-Through Rate Prediction. SIGIR 2022 【层次化意图嵌入网络】
NAS-CTR: Efficient Neural Architecture Search for Click-Through Rate Prediction. SIGIR 2022 【高效的网络结构搜索】
NMO: A Model-Agnostic and Scalable Module for Inductive Collaborative Filtering. SIGIR 2022 【模型无关的归纳式协同过滤模块】
Neighbour Interaction based Click-Through Rate Prediction via Graph-masked Transformer. SIGIR 2022 【图遮盖的Transformer】
Neural Statistics for Click-Through Rate Prediction. SIGIR 2022 【short paper，神经统计学】
Smooth-AUC: Smoothing the Path Towards Rank-based CTR Prediction. SIGIR 2022 【short paper，基于排序的CTR预估】
DisenCTR: Dynamic Graph-based Disentangled Representation for Click-Through Rate Prediction. SIGIR 2022 【基于图的解耦表示】
Deep Multi-Representational Item Network for CTR Prediction. SIGIR 2022 【short paper，多重表示商品网络】
Gating-adapted Wavelet Multiresolution Analysis for Exposure Sequence Modeling in CTR prediction. SIGIR 2022 【short paper，多分辨率小波分析】
MetaCVR: Conversion Rate Prediction via Meta Learning in Small-Scale Recommendation Scenarios. SIGIR 2022 【short paper，小规模推荐场景下的元学习】
Adversarial Filtering Modeling on Long-term User Behavior Sequences for Click-Through Rate Prediction. SIGIR 2022 【short paper，对抗过滤建模用户长期行为序列】
Clustering based Behavior Sampling with Long Sequential Data for CTR Prediction. SIGIR 2022 【short paper，长序列数据集基于聚类的行为采样】
CTnoCVR: A Novelty Auxiliary Task Making the Lower-CTR-Higher-CVR Upper. SIGIR 2022 【short paper，新颖度辅助任务】
Large-Scale Modeling of Mobile User Click Behaviors Using Deep Learning. RecSys 2021 【移动设备的用户的点击行为预测】
Page-level Optimization of e-Commerce Item Recommendations. RecSys 2021 【商品详细信息页面的商品推荐模块】
An Analysis Of Entire Space Multi-Task Models For Post-Click Conversion Prediction. RecSys 2021 【LBR，点击后转换率预测的全空间多任务模型分析】
CAEN: A Hierarchically Attentive Evolution Network for Item-Attribute-Change-Aware Recommendation in the Growing E-commerce Environment. RecSys 2022 【物品属性变化感知的分层注意力动态网络】
Dual Attentional Higher Order Factorization Machines. RecSys 2022 【双注意高阶因式分解机】
Position Awareness Modeling with Knowledge Distillation for CTR Prediction. RecSys 2022 【LBR，位置感知的知识提取框架】
APG: Adaptive Parameter Generation Network for Click-Through Rate Prediction. NIPS 2022 【点击率预测的自适应参数生成网络】
Alleviating Cold-start Problem in CTR Prediction with A Variational Embedding Learning Framework. WWW 2022 【使用变分embedding学习框架缓解 CTR 预测中的冷启动问题】
CBR: Context Bias aware Recommendation for Debiasing User Modeling and Click Prediction. WWW 2022 【去除由丰富交互造成的上下文偏差】

Knowledge-aware Recommendations

这类任务旨在利用结构化的信息辅助推荐。早期的工作聚焦于meta-path方法，近年来随着图神经网络技术的不断发展，基于GNN的方法已经成为主流方向。

A Knowledge-Aware Recommender with Attention-Enhanced Dynamic Convolutional Network. CIKM 2021【动态卷积用于知识感知的推荐】
Entity-aware Collaborative Relation Network with Knowledge Graph for Recommendation. CIKM 2021【short paper，KG+RS】
Conditional Graph Attention Networks for Distilling and Refining Knowledge Graphs in Recommendation. CIKM 2021【GNN+KG+RS】
Knowledge Enhanced Multi-Interest Network for the Generation of Recommendation Candidates. CIKM 2022 【用于生成推荐候选的知识增强多兴趣网络】
Tiger: Transferable Interest Graph Embedding for Domain-Level Zero-Shot Recommendation. CIKM 2022 【用于域级零样本推荐的可迁移兴趣图嵌入】
Improving Knowledge-aware Recommendation with Multi-level Interactive Contrastive Learning. CIKM 2022 【通过多层次交互式对比学习改进知识感知推荐】
Modeling Scale-free Graphs with Hyperbolic Geometry for Knowledge-aware Recommendation. WSDM 2022【使用双曲几何建模无标度图以进行知识感知推荐】
Knowledge Graph Contrastive Learning for Recommendation. SIGIR 2022 【知识图谱上的对比学习】
Multi-level Cross-view Contrastive Learning for Knowledge-aware Recommender System. SIGIR 2022 【多级交叉视图的对比学习】
Alleviating Spurious Correlations in Knowledge-aware Recommendations through Counterfactual Generator. SIGIR 2022 【利用反事实生成器缓解假知识】
HAKG: Hierarchy-Aware Knowledge Gated Network for Recommendation. SIGIR 2022 【层次化知识门控网络】
KETCH: Knowledge Graph Enhanced Thread Recommendation in Healthcare Forums. SIGIR 2022 【医疗论坛上的知识图谱增强的推荐】
Sparse Feature Factorization for Recommender Systems with Knowledge Graphs. RecSys 2021 【利用知识图谱分解推荐系统稀疏特征】
TinyKG: Memory-Efficient Training Framework for Knowledge Graph Neural Recommender Systems. RecSys 2022 【知识图神经推荐系统的内存高效训练框架】
Knowledge-aware Recommendations Based on Neuro-Symbolic Graph Embeddings and First-Order Logical Rules. RecSys 2022 【LBR，基于神经符号图表示的知识感知推荐框架】
Multi-level Recommendation Reasoning over Knowledge Graphs with Reinforcement Learning. WWW 2022 【基于强化学习的知识图多级推荐推理】
Path Language Modeling over Knowledge Graphs for Explainable Recommendation. WWW 2022 【在知识图谱上学习语言模型，实现推荐和解释】

Conversational Recommender System

对话推荐系统通过多轮对话，建模用户的动态偏好从而完成推荐。目前的主流技术包括强化学习对话策略；知识增强对话推荐系统；对话推荐中的可控增强；以及统一推荐、对话框架等。

Popcorn: Human-in-the-loop Popularity Debiasing in Conversational Recommender Systems. CIKM 2021【采用人在回路方式进行对话推荐系统的流行度去偏】
A Neural Conversation Generation Model via Equivalent Shared Memory Investigation. CIKM 2021【对话生成】
C2-CRS: Coarse-to-Fine Contrastive Learning for Conversational Recommender System. WSDM 2022【对话式推荐系统的粗到细对比学习】
Rethinking Conversational Recommendations: Is Decision Tree All You Need? CIKM 2022 【重新思考对话推荐：决策树是否就是我们需要的？】
Two-level Graph Path Reasoning for Conversational Recommendation with User Realistic Preference. CIKM 2022 【具有用户现实偏好的会话推荐的两级图路径推理】
Extracting Relevant Information from User's Utterances in Conversational Search and Recommendation. KDD 2022 【用户话语权】
Towards Unified Conversational Recommender Systems via Knowledge-Enhanced Prompt Learning. KDD 2022 【知识增强的提示学习】
Learning to Infer User Implicit Preference in Conversational Recommendation. SIGIR 2022 【学习推测用户隐偏好】
User-Centric Conversational Recommendation with Multi-Aspect User Modeling. SIGIR 2022 【多角度用户建模】
Variational Reasoning about User Preferences for Conversational Recommendation. SIGIR 2022 【用户偏好的变分推理】
Analyzing and Simulating User Utterance Reformulation in Conversational Recommender Systems. SIGIR 2022 【对话推荐中模仿用户言论】
Improving Conversational Recommender Systems via Transformer-based Sequential ModellingSIGIR 2022 【short paper，基于Transformer的序列化建模】
Conversational Recommendation via Hierarchical Information Modeling. SIGIR 2022 【short paper，层次化信息建模】
Large-scale Interactive Conversational Recommendation System. RecSys 2021 【大规模交互式对话推荐系统】
Partially Observable Reinforcement Learning for Dialog-based Interactive Recommendation. RecSys 2021 【将强化学习用于基于对话框的交互式推荐任务】
Generation-based vs. Retrieval-based Conversational Recommendation: A User-Centric Comparison. RecSys 2021 【Reproducibility paper，对话推荐中基于生成和基于检索的方法对比】
Soliciting User Preferences in Conversational Recommender Systems via Usage-related Questions. RecSys 2021 【LBR，对话推荐系统的偏好启发方法】
Bundle MCR: Towards Conversational Bundle Recommendation. RecSys 2022 【马尔可夫决策进行对话式捆绑推荐】
Self-Supervised Bot Play for Transcript-Free Conversational Recommendation with Rationales. RecSys 2022 【自监督对话推荐】
Multiple Choice Questions based Multi-Interest Policy Learning for Conversational Recommendation. WWW 2022 【基于多兴趣的对话推荐策略学习】

Social Recommendation

Social Recommendation with Self-Supervised Metagraph Informax Network. CIKM 2021【使用自监督元图网络的社交推荐】
Ranking Friend Stories on Social Platforms with Edge-Contextual Local Graph Convolutions. WSDM 2022 【基于图卷积神经网络的社交排序】
Socially-Aware Self-Supervised Tri-Training for Recommendation. KDD 2021 【社会意识自监督的立体推荐系统】
Affective Signals in a Social Media Recommender System. KDD 2022 【社交媒体情感信息】
I want to break free! Recommending friends from outside the echo chamber. RecSys 2021 【有回声室意识的朋友推荐方法】
The Dual Echo Chamber: Modeling Social Media Polarization for Interventional Recommending. RecSys 2021 【针对双回声室效应的社交媒体极化模型】
Auditing the Effect of Social Network Recommendations on Polarization in Geometrical Ideological Spaces. RecSys 2021 【LBR，社交网络推荐对几何意识形态空间中极化的影响】
Do recommender systems make social media more susceptible to misinformation spreaders?. RecSys 2022 【LBR，错误信息传播者对社交推荐的影响】
Revisiting Graph based Social Recommendation: A Distillation Enhanced Social Graph Network. WWW 2022 【使用知识蒸馏来融入user-item交互图和user-user社交图的信息】
Large-scale Personalized Video Game Recommendation via Social-aware Contextualized Graph Neural Network. WWW 202 【同时考虑个性化，游戏上下文，社交联系】

News Recommendation

WG4Rec: Modeling Textual Content with Word Graph for News Recommendation. CIKM 2021【使用Word Graph为新闻推荐建模文本内容】
Popularity-Enhanced News Recommendation with Multi-View Interest Representation. CIKM 2021【多视角兴趣学习的流行度增强的新闻推荐】
Prioritizing Original News on Facebook. CIKM 2021【applied paper，原创新闻优先级排序】
DeepVT: Deep View-Temporal Interaction Network for News Recommendatio. CIKM 2022 【新闻推荐的深度视图-时间交互网络】
Generative Adversarial Zero-Shot Learning for Cold-Start News Recommendation. CIKM 2022 【冷启动新闻推荐的生成对抗零样本学习】
Personalized Chit-Chat Generation for Recommendation Using External Chat Corpora. KDD 2022 【个性化聊天】
Training Large-Scale News Recommenders with Pretrained Language Models in the Loop. KDD 2022 【轻量级编码pipeline】
Reinforced Anchor Knowledge Graph Generation for News Recommendation Reasoning. KDD 2021 【新闻推荐推理的增强锚点知识图生成】
ProFairRec: Provider Fairness-aware News Recommendation. SIGIR 2022 【商家公平的新闻推荐】
Positive, Negative and Neutral: Modeling Implicit Feedback in Session-based News Recommendation. SIGIR 2022 【建模隐式反馈】
FUM: Fine-grained and Fast User Modeling for News Recommendation. SIGIR 2022 【short paper，细粒度快速的用户建模】
Is News Recommendation a Sequential Recommendation Task?. SIGIR 2022 【short paper，新闻推荐是序列化推荐吗】
News Recommendation with Candidate-aware User Modeling. SIGIR 2022 【short paper，候选感知的用户建模】
MM-Rec: Visiolinguistic Model Empowered Multimodal News Recommendation. SIGIR 2022 【short paper，视觉语言学增强的多模态新闻推荐】
RADio – Rank-Aware Divergence Metrics to Measure Normative Diversity in News Recommendations. RecSys 2022【衡量新闻推荐规范化多样性的度量框架】
Reducing Cross-Topic Political Homogenization in Content-Based News Recommendation. RecSys 2022【新闻推荐中减少跨主题的政治同质化】
FeedRec: News Feed Recommendation with Various User Feedbacks. WWW 2022 【融入各类显示/隐式反馈来建模用户兴趣】

Music Recommendation

A Case Study in Educational Recommenders:Recommending Music Partitures at Tomplay. CIKM 2022 【在 Tomplay 推荐音乐片段】
Counteracting User Attention Bias in Music Streaming Recommendation via Reward Modification. KDD 2022 【用户注意力对抗】
Follow the guides: disentangling human and algorithmic curation in online music consumption. RecSys 2021 【在线音乐消费中的人为和算法影响】
The role of preference consistency, defaults and musical expertise in users' exploration behavior in a genre exploration recommender. RecSys 2021 【用户音乐偏好的行为探索】
Analyzing Item Popularity Bias of Music Recommender Systems: Are Different Genders Equally Affected?. RecSys 2021 【LBR，音乐推荐物品流行度偏差的性别分析】
Baby Shark to Barracuda: Analyzing Children’s Music Listening Behavior. RecSys 2021 【LBR，儿童音乐行为分析】
Optimizing the Selection of Recommendation Carousels with Quantum Computing. RecSys 2021【LBR，用量子计算优化音乐歌单推荐】
Play It Again, Sam! Recommending Familiar Music in Fresh Ways. RecSys 2021【LBR，用巡演推荐重复的音乐】
Predicting Music Relistening Behavior Using the ACT-R Framework. RecSys 2021【LBR，基于心理学的理论来建模音乐重听行为】
Siamese Neural Networks for Content-based Cold-Start Music Recommendation. RecSys 2021 【LBR，暹罗神经网络进行音乐冷启动推荐】
A User-Centered Investigation of Personal Music Tours. RecSys 2022 【以用户为中心的音乐巡演推荐】
Exploiting Negative Preference in Content-based Music Recommendation with Contrastive Learning. RecSys 2022 【利用对比学习挖掘基于内容的音乐推荐中的负面偏好】
Exploring the longitudinal effect of nudging on users' genre exploration behavior and listening preference. RecSys 2022 【探索轻推对用户听歌体裁偏好的纵向效应】
Discovery Dynamics: Leveraging Repeated Exposure for User and Music CharacterizationRecSys 2022 【LBR，探索轻推对用户听歌体裁偏好的纵向效应】
Efficient Online Learning to Rank for Sequential Music Recommendation. WWW 2022 【将搜索空间限制在此前表现不佳的搜索方向的正交补上】

Text-aware Recommendation

Counterfactual Review-based Recommendation. CIKM 2021【基于评论的反事实推荐】
Review-Aware Neural Recommendation with Cross-Modality Mutual Attention. CIKM 2021【short paper，文本+RS+跨模态】
Aligning Dual Disentangled User Representations from Ratings and Textual Content. KDD 2022 【用户双重解耦表示对齐】
Collaborative Filtering with Attribution Alignment for Review-based Non-overlapped Cross Domain Recommendation. WWW 2022 【通过属性对齐实现基于评论的跨域推荐】
Accurate and Explainable Recommendation via Review Rationalization. WWW 2022 【提取评论中的因果关系】
Heterogeneous Interactive Snapshot Network for Review-Enhanced Stock Profiling and Recommendation. IJCAI 2022 【评论增强的股票分析和推荐】

POI Recommendation

Answering POI-recommendation Questions using Tourism Reviews. CIKM 2021【使用旅游者评论回答POI问题】
SNPR: A Serendipity-Oriented Next POI Recommendation Model. CIKM 2021【面向偶然性的POI推荐】
You Are What and Where You Are: Graph Enhanced Attention Network for Explainable POI Recommendation. CIKM 2021【applied paper，Attention 图神经网络用于可解释推荐】
ST-PIL: Spatial-Temporal Periodic Interest Learning for Next Point-of-Interest Recommendation. CIKM 2021【short paper，用于POI推荐的时空周期兴趣学习】
Graph-Flashback Network for Next Location Recommendation. KDD 2022 【引入POI相似度权重】
Curriculum Meta-Learning for Next POI Recommendation. KDD 2021 【基于元学习的下一代兴趣点推荐系统】
Hierarchical Multi-Task Graph Recurrent Network for Next POI Recommendation. SIGIR 2022 【多任务图循环网络】
Learning Graph-based Disentangled Representations for Next POI Recommendation. SIGIR 2022 【学习基于图的解耦表示】
GETNext: Trajectory Flow Map Enhanced Transformer for Next POI Recommendation. SIGIR 2022 【轨迹图加强的Transformer】
Next Point-of-Interest Recommendation with Auto-Correlation Enhanced Multi-Modal Transformer Network. SIGIR 2022 【short paper，自修正的多模态Transformer】
Empowering Next POI Recommendation with Multi-Relational Modeling. SIGIR 2022 【多重关系建模】
Exploring the Impact of Temporal Bias in Point-of-Interest Recommendation. RecSys 2022 【LBR，时间偏差对兴趣点推荐的影响】
Modeling Spatio-temporal Neighbourhood for Personalized Point-of-interest Recommendation. IJCAI 2022 【融入知识图谱和时域信息，实现个性化POI推荐】
Next Point-of-Interest Recommendation with Inferring Multi-step Future Preferences. IJCAI 2022 【考虑用户未来偏好】

Online Recommendation

Generative Inverse Deep Reinforcement Learning for Online Recommendation. CIKM 2021【用于在线推荐的生成式逆强化学习】
Long Short-Term Temporal Meta-learning in Online Recommendation. WSDM 2022【在线推荐中的长短期时间元学习】
A Cooperative-Competitive Multi-Agent Framework for Auto-bidding in Online Advertising. WSDM 2022【一种用于在线广告自动竞价的合作竞争多代理框架】
Knowledge Extraction and Plugging for Online Recommendation. CIKM 2022 【在线推荐的知识抽取与插入】
Real-time Short Video Recommendation on Mobile Devices. CIKM 2022 【移动端实时短视频推荐】
SASNet: Stage-aware sequential matching for online travel recommendation. CIKM 2022 【在线旅游推荐的阶段感知序列匹配】
Meta-Learning for Online Update of Recommender Systems AAAI 2022 【自适应最优学习率】
Architecture and Operation Adaptive Network for Online Recommendations. KDD 2021 【在线推荐系统的架构及其自适应网络】
Recommendation on Live-Streaming Platforms: Dynamic Availability and Repeat Consumption. RecSys 2021 【实时流平台推荐的动态可用性和重复消费】
A GPU-specialized Inference Parameter Server for Large-Scale Deep Recommendation Models. RecSys 2022 【大规模在线推理模型基于 GPU 高速缓存的分布式框架】
Modeling User Repeat Consumption Behavior for Online Novel Recommendation. RecSys 2022 【在线小说推荐的用户重复消费行为建模】

Group Recommendation

Double-Scale Self-Supervised Hypergraph Learning for Group Recommendation. CIKM 2021【用于群组推荐的自监督超图学习】
DeepGroup: Group Recommendation with Implicit Feedback. CIKM 2021【short paper，隐式反馈的群组推荐】
Multi-View Intent Disentangle Graph Networks for Bundle Recommendation. AAAI 2022 【多意图捆绑推荐】
Thinking inside The Box: Learning Hypercube Representations for Group Recommendation. SIGIR 2022 【超立方体表示用于组推荐】
Enumerating Fair Packages for Group Recommendations. WSDM 2022【枚举组推荐的公平包】
GBERT: Pre-training User representations for Ephemeral Group Recommendation. CIKM 2022 【为临时组推荐预训练用户表示】
BRUCE – Bundle Recommendation Using Contextualized item Embeddings. RecSys 2022 【Transformer 建模上下文进行捆绑推荐】
Bundle MCR: Towards Conversational Bundle Recommendation. RecSys 2022 【马尔可夫决策进行对话式捆绑推荐】

Multi-task/Multi-behavior/Cross-domain Recommendations

Multi-task Learning for Bias-Free Joint CTR Prediction and Market Price Modeling in Online Advertising. CIKM 2021【在线广告无偏差联合CTR预估和市场价格建模的多任务学习】
Cross-Market Product Recommendation. CIKM 2021【跨市场产品推荐】
Expanding Relationship for Cross Domain Recommendation. CIKM 2021【扩展跨领域推荐的关系】
Learning Representations of Inactive Users: A Cross Domain Approach with Graph Neural Networks. CIKM 2021【short paper，跨领域方法结合图神经网络用于学习非活跃用户表示】
Low-dimensional Alignment for Cross-Domain Recommendation. CIKM 2021【short paper，跨领域推荐的低维对齐】
Multi-Sparse-Domain Collaborative Recommendation via Enhanced Comprehensive Aspect Preference Learning. WSDM 2022【通过增强的综合方面偏好学习的多稀疏域协作推荐】
Leaving No One Behind: A Multi-Scenario Multi-Task Meta Learning Approach for Advertiser Modeling. WSDM 2022【一种用于广告商建模的多场景多任务元学习方法】
RecGURU: Adversarial Learning of Generalized User Representations for Cross-Domain Recommendation. WSDM 2022【用于跨域推荐的广义用户表示的对抗性学习】
Personalized Transfer of User Preferences for Cross-domain Recommendation. WSDM 2022【跨域推荐用户偏好的个性化传输】
Adaptive Domain Interest Network for Multi-domain Recommendation. CIKM 2022 【多域推荐的自适应域兴趣网络】
Multi-Scale User Behavior Network for Entire Space Multi-Task Learning. CIKM 2022 【全空间多任务学习的多尺度用户行为网络】
Gromov-Wasserstein Guided Representation Learning for Cross-Domain Recommendation. CIKM 2022 【跨域推荐表示学习】
Contrastive Cross-Domain Sequential Recommendation. CIKM 2022 【对比跨域序列推荐】
Cross-domain Recommendation via Adversarial Adaptation. CIKM 2022【通过对抗性适应进行跨域推荐】
Dual-Task Learning for Multi-Behavior Sequential Recommendation. CIKM 2022 【多行为序列推荐的双任务学习】
FedCDR: Federated Cross-Domain Recommendation for Privacy-Preserving Rating Prediction. CIKM 2022 【FedCDR：用于隐私保护评级预测的联合跨域推荐】
Leveraging Multiple Types of Domain Knowledge for Safe and Effective Drug Recommendation. CIKM 2022 【利用多种领域知识进行安全有效的药物推荐】
Multi-Faceted Hierarchical Multi-Task Learning for Recommender Systems. CIKM 2022 【推荐系统的多方面分层多任务学习】
Review-Based Domain Disentanglement without Duplicate Users or Contexts for Cross-Domain Recommendation. CIKM 2022 【没有重复用户或上下文的基于审查的域解耦，用于跨域推荐】
Scenario-Adaptive and Self-Supervised Model for Multi-Scenario Personalized Recommendation. CIKM 2022 【多场景个性化推荐的场景自适应自监督模型】
Cross-Task Knowledge Distillation in Multi-Task Recommendation. AAAI 2022 【跨任务知识蒸馏】
Towards Universal Sequence Representation Learning for Recommender Systems. KDD 2022 【引入物品描述文本】
Contrastive Cross-domain Recommendation in Matching. KDD 2022 【对比学习捕获用户兴趣】
Multi-Behavior Hypergraph-Enhanced Transformer for Sequential Recommendation. KDD 2022 【多行为超图增强】
Multi-Task Fusion via Reinforcement Learning for Long-Term User Satisfaction in Recommender Systems. KDD 2022 【Batch RL建模MTF】
CausalInt: Causal Inspired Intervention for Multi-Scenario Recommendation. KDD 2022 【多场景推荐统一框架】
Modeling the Sequential Dependence among Audience Multi-step Conversions with Multi-task Learning in Targeted Display Advertising. KDD 2021 【序列依赖多任务学习】
Learning to Expand Audience via Meta Hybrid Experts and Critics for Recommendation and Advertising. KDD 2021 【混合场景多任务学习】
Adversarial Feature Translation for Multi-domain Recommendation. KDD 2021 【对抗特征迁移多任务学习】
Debiasing Learning based Cross-domain Recommendation. KDD 2021 【跨域推荐纠偏】
Co-training Disentangled Domain Adaptation Network for Leveraging Popularity Bias in Recommenders. SIGIR 2022 【训练解耦的域适应网络来利用流行度偏差】
DisenCDR: Learning Disentangled Representations for Cross-Domain Recommendation. SIGIR 2022 【解耦表示】
Doubly-Adaptive Reinforcement Learning for Cross-Domain Interactive Recommendation. SIGIR 2022 【双重适应的强化学习】
Exploiting Variational Domain-Invariant User Embedding for Partially Overlapped Cross Domain Recommendation. SIGIR 2022 【域不变的用户嵌入】
Multi-Behavior Sequential Transformer Recommender. SIGIR 2022 【多行为序列化Transformer】
Towards Source-Aligned Variational Models for Cross-Domain Recommendation. RecSys 2021 【变分自动编码器用于跨域推荐】
An Analysis Of Entire Space Multi-Task Models For Post-Click Conversion Prediction. RecSys 2021 【LBR，点击后转换率预测的全空间多任务模型分析】
MARRS: A Framework for multi-objective risk-aware route recommendation using Multitask-Transformer. RecSys 2022 【利用多任务 Transformer 进行多目标的路线推荐】
M2TRec: Metadata-aware Multi-task Transformer for Large-scale and Cold-start free Session-based Recommendations. RecSys 2022【LBR，基于元数据和多任务 Transformer 的冷启动会话推荐系统】
MARRS: A Framework for multi-objective risk-aware route recommendation using Multitask-Transformer. RecSys 2022 【利用多任务 Transformer 进行多目标的路线推荐】
Collaborative Filtering with Attribution Alignment for Review-based Non-overlapped Cross Domain Recommendation. WWW 2022 【通过属性对齐实现基于评论的跨域推荐】
Differential Private Knowledge Transfer for Privacy-Preserving Cross-Domain Recommendation. WWW 2022 【通过可微隐私知识迁移实现源域隐私保护的跨域推荐】
MetaBalance: Improving Multi-Task Recommendations via Adapting Gradient Magnitudes of Auxiliary Tasks. WWW 2022 【动态保持辅助任务和目标任务的梯度在同一个量级】
A Contrastive Sharing Model for Multi-Task Recommendation. WWW 2022 【使用对比掩码来解决多任务中的参数冲突问题】
Self-supervised Graph Neural Networks for Multi-behavior Recommendation. IJCAI 2022 【GNN + 多行为推荐】
Re4: Learning to Re-contrast, Re-attend, Re-construct for Multi-interest Recommendation. WWW 2022 【通过re-contrast,re-attend,re-construct来增强解耦用户多兴趣表示】

Multimodal Recommendation

Pre-training Graph Transformer with Multimodal Side Information for Recommendation. ACM MM 2021 【多模态侧信息的预训练图 Transformer 用于推荐】
Review-Aware Neural Recommendation with Cross-Modality Mutual Attention. CIKM 2021【short paper，文本+RS+跨模态】
Click-Through Rate Prediction with Multi-Modal Hypergraphs. CIKM 2021【使用多模态超图的点击率预测】
Multimodal Graph Meta Contrastive Learning. CIKM 2021【short paper，多模态元图对比学习】
AutoMARS: Searching to Compress Multi-Modality Recommendation Systems. CIKM 2022 【搜索压缩多模态推荐系统】
Multimodal Meta-Learning for Cold-Start Sequential Recommendation. CIKM 2022 【冷启动序列推荐的多模态元学习】
MARIO: Modality-Aware Attention and Modality-Preserving Decoders for Multimedia Recommendation. CIKM 2022 【用于多媒体推荐的模态感知注意力和模态保留解码器】
ItemSage: Learning Product Embeddings for Shopping Recommendations at Pinterest. KDD 2022 【多模态商品推荐】
SEMI: A Sequential Multi-Modal Information Transfer Network for E-Commerce Micro-Video Recommendations. KDD 2021 【基于序列多模态信息传输网络的电商微视频推荐系统】
MM-Rec: Visiolinguistic Model Empowered Multimodal News Recommendation. SIGIR 2022 【short paper，视觉语言学增强的多模态新闻推荐】
Semi-Supervised Visual Representation Learning for Fashion Compatibility. RecSys 2021 【搭配时装预测的半监督视觉表征学习】
Tops, Bottoms, and Shoes: Building Capsule Wardrobes via Cross-Attention Tensor Network. RecSys 2021 【通过视觉的交叉注意力张力网络提供服饰搭配推荐】
Multi-Modal Dialog State Tracking for Interactive Fashion Recommendation. RecSys 2022 【交互式时装推荐的多模态注意网络】

Other Tasks

除了上述的较为经典的推荐任务，最近的顶会文章还有一些其他有意思的任务。

Learning An End-to-End Structure for Retrieval in Large-Scale Recommendations. CIKM 2021【在大规模推荐中学习一个端到端的结构用于检索】
USER: A Unified Information Search and Recommendation Model based on Integrated Behavior Sequence. CIKM 2021【基于集成行为序列的统一搜索与推荐模型】
Multi-hop Reading on Memory Neural Network with Selective Coverage for Medication Recommendation. CIKM 2021【药物推荐】
Show Me the Whole World: Towards Entire Item Space Exploration for Interactive Personalized Recommendations. WSDM 2022【面向交互式个性化推荐的整个商品空间探索】
Adapting Triplet Importance of Implicit Feedback for Personalized Recommendation. CIKM 2022 【在个性化推荐中调整隐式反馈的三元组重要性】
GRP: A Gumbel-based Rating Prediction Framework for Imbalanced Recommendation. CIKM 2022 【基于 Gumbel 的不平衡推荐评级预测框架】
Rank List Sensitivity of Recommender Systems to Interaction Perturbations. CIKM 2022 【推荐系统对交互扰动的排名列表敏感性】
CROLoss: Towards a Customizable Loss for Retrieval Models in Recommender Systems. CIKM 2022 【推荐系统中检索模型的可定制损失】
Towards Principled User-side Recommender Systems. CIKM 2022 【迈向有原则的用户侧推荐系统】
UDM: A Unified Deep Matching Framework in Recommender System. CIKM 2022 【推荐系统中的统一深度匹配框架】
User Recommendation in Social Metaverse with VR. CIKM 2022 【VR 的用户推荐】
AdaFS: Adaptive Feature Selection in Deep Recommender System. KDD 2022 【自适应特征选择】
CAPTOR: A Crowd-Aware Pre-Travel Recommender System for Out-of-Town Users. SIGIR 2022 【为乡村用户提供的旅游推荐】
PERD: Personalized Emoji Recommendation with Dynamic User Preference. SIGIR 2022 【short paper，个性化表情推荐】
Item Similarity Mining for Multi-Market Recommendation. SIGIR 2022 【short paper，多市场推荐中的商品相似度挖掘】
A Content Recommendation Policy for Gaining Subscribers. SIGIR 2022 【short paper，为提升订阅者的内容推荐策略】
Accordion: A Trainable Simulator for Long-Term Interactive Systems. RecSys 2021 【长期交互系统的可训练模拟器】
Information Interactions in Outcome Prediction: Quantification and Interpretation using Stochastic Block Models. RecSys 2021 【结果预测中的信息交互】
Local Factor Models for Large-Scale Inductive Recommendation. RecSys 2021 【归纳推荐的局部因子模型】
Reverse Maximum Inner Product Search: How to efficiently find users who would like to buy my item?. RecSys 2021 【反向最大内部产品搜索】
“Serving Each User”: Supporting Different Eating Goals Through a Multi-List Recommender Interface. RecSys 2021 【通过多列表推荐界面个性化食品推荐】
An Interpretable Recommendation Model for Gerontological Care. RecSys 2021【LBR，老年护理的推荐研究】
Automatic Collection Creation and Recommendation. RecSys 2021【LBR，自动创建和推荐收藏夹】
Estimating and Penalizing Preference Shifts in Recommender Systems. RecSys 2021【LBR，推荐系统中偏好转移的分析】
Global-Local Item Embedding for Temporal Set Prediction. RecSys 2021【LBR，时间集预测任务】
Modeling Two-Way Selection Preference for Person-Job Fit. RecSys 2022 【建模双向选择偏好的人岗匹配模型】
Towards Psychologically Grounded Dynamic Preference Models. RecSys 2022 【基于心理学的动态偏好建模】

2. Topic

Debias in Recommender System

推荐系统去偏旨在消除推荐数据/模型中由偏差带来的不良影响。其中偏差包括比较常见的流行度偏差 (popularity bias)，选择偏差 (selection bias)，曝光偏差 (exposure bias)，位置偏差 (position bias) 以及其他各种偏差。目前的主流技术包括解耦用户表示，从因果角度进行解耦；推理阶段合理利用偏差，通过在推理阶段注入偏差来消除训练期间的偏差影响；关注动态场景下如何消除偏差等。

Unbiased Filtering of Accidental Clicks in Verizon Media Native Advertising. CIKM 2021【applied paper，广告意外点击的无偏过滤】
CauSeR: Causal Session-based Recommendations for Handling Popularity Bias. CIKM 2021【short paper，用于流行度去偏的因果关系序列推荐】
It Is Different When Items Are Older: Debiasing Recommendations When Selection Bias and User Preferences are Dynamic. WSDM 2022【选择偏差和偏好偏差动态变化时的纠偏推荐系统】
Fighting Mainstream Bias in Recommender Systems via Local Fine Tuning. WSDM 2022【通过局部微调对抗推荐系统中的主流偏见】
Towards Unbiased and Robust Causal Ranking for Recommender Systems. WSDM 2022【推荐系统的无偏和稳健因果排名】
Quantifying and Mitigating Popularity Bias in Conversational Recommender Systems. CIKM 2022 【量化和减轻会话推荐系统中的流行度偏差】
Learning Unbiased User Behaviors Estimation with Hierarchical Recurrent Model on the Entire Space. CIKM 2022 【分层递归模型学习无偏用户行为估计】
Representation Matters When Learning From Biased Feedback in Recommendation. CIKM 2022 【从推荐中的有偏反馈中学习时，表征很重要】
Invariant Preference Learning for General Debiasing in Recommendation. KDD 2022 【不变偏好解耦】
Counteracting User Attention Bias in Music Streaming Recommendation via Reward Modification. KDD 2022 【用户注意力对抗】
Deconfounding Duration Bias in Watch-time Prediction for Video Recommendation. KDD 2022 【视频时长去偏】
Debiasing the Cloze Task in Sequential Recommendation with Bidirectional Transformers. KDD 2022 【序列完形填空去偏】
Debiasing Learning for Membership Inference Attacks Against Recommender Systems. KDD 2022 【VAE 去偏】
Popularity Bias in Dynamic Recommendation. KDD 2021 【动态推荐系统的热度纠偏】
Debiasing Learning based Cross-domain Recommendation. KDD 2021 【跨域推荐纠偏】
Model-Agnostic Counterfactual Reasoning for Eliminating Popularity Bias in Recommender System. KDD 2021 【不可知反事实推理模型消除推荐系统的流行偏差】
Interpolative Distillation for Unifying Biased and Debiased Recommendation
Co-training Disentangled Domain Adaptation Network for Leveraging Popularity Bias in Recommenders. SIGIR 2022 【训练解耦的域适应网络来利用流行度偏差】
Bilateral Self-unbiased Recommender Learning from Biased Implicit Feedback. SIGIR 2022 【双边去偏】
Mitigating Consumer Biases in Recommendations with Adversarial Training. SIGIR 2022 【short paper，对抗训练去偏】
Neutralizing Popularity Bias in Recommendation Models. SIGIR 2022 【short paper，中和流行度偏差】
DeSCoVeR: Debiased Semantic Context Prior for Venue Recommendation. SIGIR 2022 【short paper，在场所推荐中去除语义上下文先验】
An Audit of Misinformation Filter Bubbles on YouTube: Bubble Bursting and Recent Behavior Changes. RecSys 2021 【虚假信息过滤气泡的审计：走出信息茧房并改变近期行为】
Debiased Explainable Pairwise Ranking from Implicit Feedback. RecSys 2021【去偏的可解释贝叶斯个性化排名】
Mitigating Confounding Bias in Recommendation via Information Bottleneck. RecSys 2021【信息瓶颈缓解混杂偏倚】
User Bias in Beyond-Accuracy Measurement of Recommendation Algorithms. RecSys 2021【超精度测量中的算法用户偏差】
Analyzing Item Popularity Bias of Music Recommender Systems: Are Different Genders Equally Affected?. RecSys 2021 【LBR，音乐推荐物品流行度偏差的性别分析】
The Idiosyncratic Effects of Adversarial Training on Bias in Personalized Recommendation Learning. RecSys 2021 【LBR，对抗训练对流行度偏差的影响研究】
Transfer Learning in Collaborative Recommendation for Bias Reduction. RecSys 2021 【LBR，减少偏差的迁移学习】
Countering Popularity Bias by Regularizing Score Differences. RecSys 2022 【利用正则化分数差异减少流行度偏差】
Off-Policy Actor Critic for Recommender Systems. RecSys 2022 【离线演员-评论家强化学习算法缓解分布偏差问题】
Exploring the Impact of Temporal Bias in Point-of-Interest Recommendation. RecSys 2022 【LBR，时间偏差对兴趣点推荐的影响】
Trading Hard Negatives and True Negatives: A Debiased Contrastive Collaborative Filtering Approach. IJCAI 2022 【探索正确的负样本】
Debiased, Longitudinal and Coordinated Drug Recommendation through Multi-Visit Clinic Records. NIPS 2022 【去偏药物推荐】
CBR: Context Bias aware Recommendation for Debiasing User Modeling and Click Prediction. WWW 2022 【去除由丰富交互造成的上下文偏差】
UKD: Debiasing Conversion Rate Estimation via Uncertainty-regularized Knowledge Distillation. WWW 2022 【基于不确定性正则化和知识提取的转化率估计去偏】

Fairness in Recommender System

推荐系统的公平性指在个性化推荐时进一步考虑推荐的公平性。目前的主流技术包括引入公平性指标，在训练时同时优化准确性和公平性的指标；因果推断去偏，采用因果推断理论缓解偏差问题，从而提升公平性；对抗学习方法，采用 GAN 等对抗训练方法，在训练中引入公平性的权衡；推荐结果重排序，在已有推荐结果上重新排序，兼顾准确性和公平性等。

SAR-Net: A Scenario-Aware Ranking Network for Personalized Fair Recommendation in Hundreds of Travel Scenarios. CIKM 2021【applied paper，用于个性化公平推荐的场景感知排名网络】
Enumerating Fair Packages for Group Recommendations. WSDM 2022【枚举组推荐的公平包】
Toward Pareto Efficient Fairness-Utility Trade-off in Recommendation through Reinforcement Learning. WSDM 2022【通过强化学习在推荐中实现帕累托高效的公平-效用权衡】
Make Fairness More Fair: Fair Item Utility Estimation and Exposure Re-Distribution. KDD 2022 【物品公平效益】
Comprehensive Fair Meta-learned Recommender System. KDD 2022 【元学习公平性框架】
Online Certification of Preference-Based Fairness for Personalized Recommender Systems. AAAI 2022 【强化学习探索】
Joint Multisided Exposure Fairness for Recommendation. SIGIR 2022 【综合考虑多边的曝光公平性】
ProFairRec: Provider Fairness-aware News Recommendation. SIGIR 2022 【商家公平的新闻推荐】
CPFair: Personalized Consumer and Producer Fairness Re-ranking for Recommender Systems. SIGIR 2022 【用户和商家公平的重排序】
Explainable Fairness for Feature-aware Recommender Systems. SIGIR 2022 【考虑特征的推荐系统中的可解释公平】
Selective Fairness in Recommendation via Prompts. SIGIR 2022 【short paper，通过提示保证可选的公平性】
Regulating Provider Groups Exposure in Recommendations. SIGIR 2022 【short paper，调整商家组曝光】
Adversary or Friend? An adversarial Approach to Improving Recommender Systems. RecSys 2022 【对抗式方法促进推荐系统公平性】
Fairness-aware Federated Matrix Factorization. RecSys 2022 【结合差异隐私技术的公平感知的联邦矩阵分解】
Toward Fair Federated Recommendation Learning: Characterizing the Inter-Dependence of System and Data Heterogeneity. RecSys 2022 【推荐中公平的联邦学习】
Link Recommendations for PageRank Fairness. WWW 2022 【PageRank算法链接预测中的公平性】
FairGAN: GANs-based Fairness-aware Learning for Recommendations with Implicit Feedback. WWW 2022 【将物品曝光公平性问题映射为隐式反馈数据中缺乏负反馈的问题】

Attack in Recommender System

PipAttack: Poisoning Federated Recommender Systems for Manipulating Item Promotion. WSDM 2022【用于操纵项目促销的中毒联合推荐系统】
FedAttack: Effective and Covert Poisoning Attack on Federated Recommendation via Hard Sampling. KDD 2022 【联邦推荐的对抗攻击】
Knowledge-enhanced Black-box Attacks for Recommendations. KDD 2022 【知识图谱增强】
Debiasing Learning for Membership Inference Attacks Against Recommender Systems. KDD 2022 【VAE去偏】
Data Poisoning Attack against Recommender System Using Incomplete and Perturbed Data. KDD 2021 【不完整及扰动数据攻击推荐系统】
Initialization Matters: Regularizing Manifold-informed Initialization for Neural Recommendation Systems. KDD 2021 【基于正则化信息的流形神经网络推荐系统】
Triple Adversarial Learning for Influence based Poisoning Attack in Recommender Systems. KDD 2021 【三元对抗学习在推荐系统中毒攻击】
Black-Box Attacks on Sequential Recommenders via Data-Free Model Extraction. RecSys 2021 【序列推荐的黑盒攻击】
Defending Substitution-Based Profile Pollution Attacks on Sequential Recommenders. RecSys 2022 【序列推荐中基于替代的对抗性攻击算法】
Revisiting Injective Attacks on Recommender Systems. NIPS 2022 【重新审视对推荐系统的注入式攻击】

Explanation in Recommender System

可解释推荐要求推荐系统不仅要提供高质量的推荐，还要对结果做出解释。目前的主流技术包括基于强化学习，将推荐模型作为环境的一部分，并对生成的解释做出奖励；基于反事实，因果推断，基于因果推断框架量化推荐理由，分析关键因素；基于知识图谱，利用知识的语义捕捉实体关系，提升解释质量；基于预训练语言模型，利用预训练语言模型生成个性化的高质量解释

Counterfactual Explainable Recommendation. CIKM 2021【反事实可解释推荐】
On the Diversity and Explainability of Recommender Systems: A Practical Framework for Enterprise App Recommendation. CIKM 2021【applied paper，推荐系统的多样性和可解释性】
You Are What and Where You Are: Graph Enhanced Attention Network for Explainable POI Recommendation. CIKM 2021【applied paper，Attention 图神经网络用于可解释推荐】
XPL-CF: Explainable Embeddings for Feature-based Collaborative Filtering. CIKM 2021【short paper，可解释 Embedding 用于基于特征的协同过滤】
Reinforcement Learning over Sentiment-Augmented Knowledge Graphs towards Accurate and Explainable Recommendation. WSDM 2022【对情感增强知识图的强化学习以实现准确和可解释的推荐】
Explanation Guided Contrastive Learning for Sequential Recommendation. CIKM 2022 【序列推荐的解释引导对比学习】
PARSRec: Explainable Personalized Attention-fused Recurrent Sequential Recommendation Using Session Partial Actions. KDD 2022 【用户个性化区分】
Post Processing Recommender Systems with Knowledge Graphs for Recency, Popularity, and Diversity of Explanations. SIGIR 2022 【使用知识图谱为推荐生成崭新的、多样的解释】
PEVAE: A hierarchical VAE for personalized explainable recommendation.. SIGIR 2022 【利用层次化VAE进行个性化可解释推荐】
Explainable Session-based Recommendation with Meta-Path Guided Instances and Self-Attention Mechanism. SIGIR 2022 【short paper，基于元路径指导和自注意力机制的可解释会话推荐】
Debiased Explainable Pairwise Ranking from Implicit Feedback. RecSys 2021【去偏的可解释贝叶斯个性化排名】
EX3: Explainable Attribute-aware Item-set Recommendations. RecSys 2021【基于物品集属性的可解释推荐】
Do Users Appreciate Explanations of Recommendations? An Analysis in the Movie Domain. RecSys 2021【LBR，电影推荐系统中用户对解释的满意度分析】
ProtoMF: Prototype-based Matrix Factorization for Effective and Explainable Recommendations. RecSys 2022【基于原型的可解释协同过滤算法】
Graph-based Extractive Explainer for Recommendations. WWW 2022 【使用图注意力网络来实现可解释推荐】
ExpScore: Learning Metrics for Recommendation Explanation. WWW 2022 【可解释推荐评价指标】
Path Language Modeling over Knowledge Graphs for Explainable Recommendation. WWW 2022 【在知识图谱上学习语言模型，实现推荐和解释】
Accurate and Explainable Recommendation via Review Rationalization. WWW 2022 【提取评论中的因果关系】
AmpSum: Adaptive Multiple-Product Summarization towards Improving Recommendation Captions. WWW 2022 【生成商品标题】
Comparative Explanations of Recommendations. WWW 2022 【可比较的推荐解释】
Neuro-Symbolic Interpretable Collaborative Filtering for Attribute-based Recommendation. WWW 2022 【以模型为核心的神经符号可解释协同过滤】
Multi-level Recommendation Reasoning over Knowledge Graphs with Reinforcement Learning. WWW 2022 【基于强化学习的知识图多级推荐推理】

Long-tail/Cold-start in Recommendations

从有推荐系统开始就存在的痛点问题，目前比较流行基于meta-learning,transfer-learning的方法。

CMML: Contextual Modulation Meta Learning for Cold-Start Recommendation. CIKM 2021【元学习+冷启动】
Reinforcement Learning to Optimize Lifetime Value in Cold-Start Recommendation. CIKM 2021【增强学习+冷启动】
Zero Shot on the Cold-Start Problem: Model-Agnostic Interest Learning for Recommender Systems. CIKM 2021【零样本学习+冷启动】
Memory Bank Augmented Long-tail Sequential Recommendation. CIKM 2022 【记忆库增强】
GIFT: Graph-guIded Feature Transfer for Cold-Start Video Click-Through Rate Prediction. CIKM 2022 【GIFT：用于冷启动视频点击率预测的图引导特征迁移】
Task-optimized User Clustering based on Mobile App Usage for Cold-start Recommendations. KDD 2022 【用户聚类】
A Dynamic Meta-Learning Model for Time-Sensitive Cold-Start Recommendations. AAAI 2022 【元学习动态推荐框架】
SMINet: State-Aware Multi-Aspect Interests Representation Network for Cold-Start Users Recommendation. AAAI 2022 【状态感知多方面兴趣网络】
Multi-view Denoising Graph Auto-Encoders on Heterogeneous Information Networks for Cold-start Recommendation. KDD 2021 【异构信息网络多视图去噪图自动编码器实现冷启动】
A Semi-Personalized System for User Cold Start Recommendation on Music Streaming Apps. KDD 2021 【半个性化的音乐流媒体应用冷启动推荐系统】
Socially-aware Dual Contrastive Learning for Cold-Start Recommendation. SIGIR 2022 【short paper，社交感知的双重对比学习】
Transform Cold-Start Users into Warm via Fused Behaviors in Large-Scale Recommendation. SIGIR 2022 【short paper，通过融合行为转换冷启动用户】
Generative Adversarial Framework for Cold-Start Item Recommendation. SIGIR 2022 【short paper，针对冷启动商品的生成对抗框架】
Improving Item Cold-start Recommendation via Model-agnostic Conditional Variational Autoencoder. SIGIR 2022 【short paper，模型无关的自编码器提升商品冷启动推荐】
Cold Start Similar Artists Ranking with Gravity-Inspired Graph Autoencoders. RecSys 2021 【图自动编码器冷启动相似艺术家排序问题】
Shared Neural Item Representations for Completely Cold Start Problem. RecSys 2021 【通过共享物品表示解决完全冷启动问题】
Siamese Neural Networks for Content-based Cold-Start Music Recommendation. RecSys 2021 【LBR，暹罗神经网络进行音乐冷启动推荐】
Fast And Accurate User Cold-Start Learning Using Monte Carlo Tree Search. RecSys 2022 【蒙特卡洛树搜索进行用户冷启动学习】
M2TRec: Metadata-aware Multi-task Transformer for Large-scale and Cold-start free Session-based Recommendations. RecSys 2022【LBR，基于元数据和多任务 Transformer 的冷启动会话推荐系统】
Alleviating Cold-start Problem in CTR Prediction with A Variational Embedding Learning Framework. WWW 2022 【使用变分embedding学习框架缓解 CTR 预测中的冷启动问题】
PNMTA: A Pretrained Network Modulation and Task Adaptation Approach for User Cold-Start Recommendation. WWW 2022 【加入编码调制器和预测调制器，使得编码器和预测器可以自适应处理冷启动用户。】
KoMen: Domain Knowledge Guided Interaction Recommendation for Emerging Scenarios. WWW 2022 【元学习+图网络】

Diversity in Recommendation

多样化的推荐结果应该尽可能包含不同的商品来满足用户的多种兴趣。目前的主流技术包括基于数据增广；基于动态的图神经网络；多目标联合优化；强化学习等。

P-Companion: A Principled Framework for Diversified Complementary Product Recommendation. CIKM 2021. PDF 【多元化补充产品推荐的原则框架】
Sliding Spectrum Decomposition for Diversified Recommendation. KDD 2021. PDF 【滑动频谱分解以实现多样化推荐】
Enhancing Domain-Level and User-Level Adaptivity in Diversified Recommendation. SIGIR 2021. PDF 【在多元化推荐中提高域级和用户级适应性】
Graph Meta Network for Multi-Behavior Recommendation with Interaction Heterogeneity and Diversity. SIGIR 2021 【结合交互异质性和多样性的多行为推荐图元网络】
Modeling Intent Graph for Search Result Diversification. SIGIR 2021 【建模意向网络用于搜索结果多样性】
Dynamic Graph Construction for Improving Diversity of Recommendation. RecSys 2021. PDF 【改进推荐多样性的动态图构建】
Towards Unified Metrics for Accuracy and Diversity for Recommender Systems. RecSys 2021. PDF 【为推荐系统建立准确性和多样性的统一指标】
On the Diversity and Explainability of Recommender Systems: A Practical Framework for Enterprise App Recommendation. CIKM 2021. PDF 【applied paper，推荐系统的多样性和可解释性】
Choosing the Best of All Worlds: Accurate, Diverse, and Novel Recommendations through Multi-Objective Reinforcement Learning. WSDM 2022【通过多目标强化学习的准确、多样化和新颖的推荐】
Feature-aware Diversified Re-ranking with Disentangled Representations for Relevant Recommendation. KDD 2022 【特征表示解耦去噪】
DAWAR: Diversity-aware Web APIs Recommendation for Mashup Creation based on Correlation Graph. SIGIR 2022 【多样化Web API推荐】
Mitigating the Filter Bubble while Maintaining Relevance: Targeted Diversification with VAE-based Recommender Systems. SIGIR 2022 【short paper，定向多样化】
Diversity vs Relevance: a practical multi-objective study in luxury fashion recommendations. SIGIR 2022 【short paper，奢侈品推荐中的多目标研究】
Towards Unified Metrics for Accuracy and Diversity for Recommender Systems. RecSys 2021 【推荐系统准确性和多样性的统一度量】
Dynamic Graph Construction for Improving Diversity of Recommendation. RecSys 2021 【LBR，改进推荐系统多样性的动态多样图框架】
Solving Diversity-Aware Maximum Inner Product Search Efficiently and Effectively. RecSys 2022 【多样性感知的最大内部产品搜索】

Denoising in Recommendation

Denoising Implicit Feedback for Recommendation. WSDM 2021 【推荐隐反馈的去噪】
The World is Binary: Contrastive Learning for Denoising Next Basket Recommendation. SIGIR 2021 【通过对比学习对下一篮推荐问题去噪】
Concept-Aware Denoising Graph Neural Network for Micro-Video Recommendation. CIKM 2021【用于微视频推荐的去噪GNN】
Hierarchical Item Inconsistency Signal learning for Sequence Denoising in Sequential Recommendation. CIKM 2022 【序列推荐中序列去噪的分层项目不一致信号学习】
Multi-view Denoising Graph Auto-Encoders on Heterogeneous Information Networks for Cold-start Recommendation. KDD 2021 【面向冷启动推荐的异构信息网络多视图去噪图自动编码器】
Learning to Denoise Unreliable Interactions for Graph Collaborative Filtering. SIGIR 2022 【数据去噪】
Less is More: Reweighting Important Spectral Graph Features for Recommendation. SIGIR 2022 【评估重要的图谱特征】
Denoising Time Cycle Modeling for Recommendation. SIGIR 2022 【short paper，去噪时间循环建模】
Denoising User-aware Memory Network for Recommendation. RecSys 2021 【用户感知记忆网络的去噪】
Denoising Self-Attentive Sequential Recommendation. RecSys 2022 【基于 Transformer 的序列推荐中自注意力机制的去噪】

Privacy Protection in Recommendation

推荐系统的隐私保护旨在保护用户隐私的前提下进行推荐。目前的研究热点包括联邦学习加密优化，结合密码学方法或模糊化方法,进一步优化安全性；联邦学习效率优化，基于采样算法研究加快收敛速度、减少通讯次数等。

FedCDR: Federated Cross-Domain Recommendation for Privacy-Preserving Rating Prediction. CIKM 2022 【FedCDR：用于隐私保护评级预测的联合跨域推荐】
PipAttack: Poisoning Federated Recommender Systems for Manipulating Item Promotion. WSDM 2022【用于操纵项目促销的中毒联合推荐系统】
FedAttack: Effective and Covert Poisoning Attack on Federated Recommendation via Hard Sampling. KDD 2022 【联邦推荐的对抗攻击】
Privacy-Preserving Synthetic Data Generation for Recommendation. SIGIR 2022 【隐私保护的仿真数据生成】
Privacy Preserving Collaborative Filtering by Distributed Mediation. RecSys 2021【隐私保护式协同过滤】
A Payload Optimization Method for Federated Recommender Systems. RecSys 2021 【联邦推荐的有效负载优化方法】
Stronger Privacy for Federated Collaborative Filtering With Implicit Feedback. RecSys 2021【隐式数据的联邦推荐系统】
FR-FMSS: Federated Recommendation via Fake Marks and Secret Sharing. RecSys 2021【LBR，跨用户联邦推荐框架】
Horizontal Cross-Silo Federated Recommender Systems. RecSys 2021【LBR，联邦推荐对多类利益相关者的影响研究】
Dynamic Global Sensitivity for Differentially Private Contextual Bandits. RecSys 2022 【通过差分私有的上下文 Bandit 算法保护隐私】
EANA: Reducing Privacy Risk on Large-scale Recommendation Models. RecSys 2022 【降低大规模推荐模型的隐私风险】
Fairness-aware Federated Matrix Factorization. RecSys 2022 【结合差异隐私技术的公平感知的联邦矩阵分解】
Toward Fair Federated Recommendation Learning: Characterizing the Inter-Dependence of System and Data Heterogeneity. RecSys 2022 【推荐中公平的联邦学习】
Poisoning Deep Learning based Recommender Model in Federated Learning Scenarios. IJCAI 2022 【设计针对基于深度学习的推荐模型的攻击】
Differential Private Knowledge Transfer for Privacy-Preserving Cross-Domain Recommendation. WWW 2022 【通过可微隐私知识迁移实现源域隐私保护的跨域推荐】

Evaluation of Recommender System

librec-auto: A Tool for Recommender Systems Experimentation. CIKM 2021 【librec-auto：推荐系统实验的工具】
RecBole: Towards a Unified, Comprehensive and Efficient Framework for Recommendation Algorithms. CIKM 2021 【RecBole：迈向统一、全面和高效的推荐算法框架】
RecBole 2.0: Towards a More Up-to-Date Recommendation Library. CIKM 2022 【RecBole 2.0：与时俱进的推荐库】
Best practices for top-N recommendation evaluation: Candidate set sampling and Statistical inference techniques. CIKM 2022 【候选集抽样和统计推断技术】
KuaiRec: A Fully-observed Dataset and Insights for Evaluating Recommender Systems. CIKM 2022 【用于评估推荐系统的完全观察数据集和见解】
FPAdaMetric: False-Positive-Aware Adaptive Metric Learning for Session-Based Recommendation. AAAI 2022 【度量学习正则化】
Evaluation of Herd Behavior Caused by Population-scale Concept Drift in Collaborative Filtering. SIGIR 2022 【short paper】
Evaluating Off-Policy Evaluation: Sensitivity and Robustness. RecSys 2021 【离线评估的可解释性评估】
Online Evaluation Methods for the Causal Effect of Recommendations. RecSys 2021 【推荐中因果效应的在线评估方法】
Towards Unified Metrics for Accuracy and Diversity for Recommender Systems. RecSys 2021 【推荐系统准确性和多样性的统一度量】
Values of Exploration in Recommender Systems. RecSys 2021 【基于强化学习推荐算法的用户探索和指标评测】
A Case Study on Sampling Strategies for Evaluating Neural Sequential Item Recommendation Models. RecSys 2021 【Reproducibility paper，序列推荐模型评测策略的研究】
Quality Metrics in Recommender Systems: Do We Calculate Metrics Consistently?. RecSys 2021 【LBR，推荐系统评估指标的再思考】
Don't recommend the obvious: estimate probability ratios. RecSys 2022 【通过拟合逐点的互信息来改进序列推荐的流行度采样指标】
RADio – Rank-Aware Divergence Metrics to Measure Normative Diversity in News Recommendations. RecSys 2022【衡量新闻推荐规范化多样性的度量框架】
A Systematic Review and Replicability Study of BERT4Rec for Sequential Recommendation. RecSys 2022【Reproducibility paper，BERT4Rec 结果的系统回顾与可复现性研究】
Revisiting the Performance of iALS on Item Recommendation Benchmarks. RecSys 2022【Reproducibility paper，隐式交替最小二乘法 iALS 基准表现的再思考】
Measuring Commonality in Recommendation of Cultural Content: Recommender Systems to Enhance Cultural Citizenship. RecSys 2022【LBR，通用性作为文化内容推荐的度量】
Multiobjective Evaluation of Reinforcement Learning Based Recommender Systems. RecSys 2022【LBR，基于强化学习的推荐系统的多目标评价】
Tenrec: A Large-scale Multipurpose Benchmark Dataset for Recommender Systems. NIPS 2022 【推荐系统的大规模多用途基准数据集】
On the Generalizability and Predictabilityof Recommender Systems. NIPS 2022 【提出一种元学习方法，针对一个全新的，未见过的数据集选择最优算法和参数】

800 篇顶会论文纵览推荐系统的前沿进展

悦读