WSDM2022推荐系统论文集锦

2022年第15届国际网络搜索与数据挖掘会议WSDM将在2022年2月21日到25日于线上举行。今年此次会议共收到了786份有效投稿，最终录取篇数为159篇，录取率为20.23%。该会议历年的论文投稿量以及接收率可见下图。

作为主流的搜索与数据挖掘会议，论文的话题主要侧重于搜索、推荐以及数据挖掘领域，因此该会议大部分的接收论文的主题是围绕着信息检索与推荐系统来说的。若想了解去年以及前年WSDM相关信息可参考：

• WSDM2021推荐系统论文集锦
• WSDM2020推荐系统论文清单

该会议将举办一些围绕信息检索、推荐系统相关的教程，其中可以重点关注下基于图神经网络的推荐系统教程，以下为教程的大纲：

推荐系统相关文章

接下来，特意从159篇论文中筛选出与推荐系统强相关的34篇文章供大家欣赏，其中从主题上看大致包括了序列推荐、跨域推荐、点击率预估、在线推荐、去偏推荐、联邦推荐、对话推荐、知识图谱推荐、组推荐、会话推荐、可解释性推荐以及路线推荐等。

从所使用的技术上划分主要采用了在线学习、元学习、强化学习、对抗训练、图神经网络、对比学习、随机游走、迁移学习等。

下文将列出相关的论文，供大家提前领略学术前沿趋势与牛人的最新想法。

跨域推荐

RecGURU: Adversarial Learning of Generalized User Representations for Cross-Domain Recommendation

https://arxiv.org/pdf/2111.10093.pdf

Personalized Transfer of User Preferences for Cross-domain Recommendation

https://arxiv.org/pdf/2110.11154.pdf

Multi-Sparse-Domain Collaborative Recommendation via Enhanced Comprehensive Aspect Preference Learning

序列推荐

Contrastive Learning for Representation Degeneration Problem in Sequential Recommendation

https://arxiv.org/pdf/2110.05730.pdf

S-Walk: Accurate and Scalable Session-based Recommendation with Random Walks

Heterogeneous Global Graph Neural Networks for Personalized Session-based Recommendation

https://arxiv.org/pdf/2107.03813.pdf

Learning Multi-granularity Consecutive User Intent Unit for Session-based Recommendation

点击率预估

CAN: Feature Co-Action Network for Click-Through Rate Prediction

Triangle Graph Interest Network for Click-through Rate Prediction

Modeling Users’ Contextualized Page-wise Feedback for Click-Through Rate Prediction in E-commerce Search

去偏推荐

It Is Different When Items Are Older: Debiasing Recommendations When Selection Bias and User Preferences are Dynamic

https://arxiv.org/pdf/2111.12481.pdf

Fighting Mainstream Bias in Recommender Systems via Local Fine Tuning

http://people.tamu.edu/~zhuziwei/pubs/Ziwei_WSDM_2022.pdf

Towards Unbiased and Robust Causal Ranking for Recommender Systems

路径推荐

PLdFe-RR:Personalized Long-distance Fuel-efficient Route Recommendation Based On Historical Trajectory

联邦推荐

PipAttack: Poisoning Federated Recommender Systems for Manipulating Item Promotion

https://arxiv.org/pdf/2110.10926.pdf

基于图结构的推荐

Joint Learning of E-commerce Search and Recommendation with A Unified Graph Neural Network

Profiling the Design Space for Graph Neural Networks based Collaborative Filtering

http://www.shichuan.org/doc/125.pdf

Graph Logic Reasoning for Recommendation and Link Prediction

Modeling Scale-free Graphs with Hyperbolic Geometry for Knowledge-aware Recommendation

https://arxiv.org/pdf/2108.06468.pdf

公平性推荐

Toward Pareto Efficient Fairness-Utility Trade-off in Recommendation through Reinforcement Learning

Enumerating Fair Packages for Group Recommendations

https://arxiv.org/pdf/2105.14423.pdf

基于对比学习的推荐

Contrastive Meta Learning with Behavior Multiplicity for Recommendation

C2-CRS: Coarse-to-Fine Contrastive Learning for Conversational Recommender System

基于元学习的推荐

Long Short-Term Temporal Meta-learning in Online Recommendation

https://arxiv.org/pdf/2105.03686.pdf

基于对抗学习的推荐

A Peep into the Future: Adversarial Future Encoding in Recommendation

基于强化学习的推荐

Reinforcement Learning over Sentiment-Augmented Knowledge Graphs towards Accurate and Explainable Recommendation

A Cooperative-Competitive Multi-Agent Framework for Auto-bidding in Online Advertising

https://arxiv.org/pdf/2106.06224.pdf

Choosing the Best of All Worlds: Accurate, Diverse, and Novel Recommendations through Multi-Objective Reinforcement Learning

https://arxiv.org/pdf/2110.15097.pdf

关于数据集

On Sampling Collaborative Filtering Datasets

The Datasets Dilemma: How Much Do We Really Know About Recommendation Datasets?

其他

VAE++: Variational AutoEncoder for Heterogeneous One-Class Collaborative Filtering

Sequential Modeling with Multiple Attributes for Watchlist Recommendation in E-Commerce

https://arxiv.org/pdf/2110.11072.pdf

Show Me the Whole World: Towards Entire Item Space Exploration for Interactive Personalized Recommendations

https://arxiv.org/pdf/2110.09905.pdf

Supervised Advantage Actor-Critic for Recommender Systems

https://arxiv.org/pdf/2111.03474.pdf

官网接收论文列表地址：

https://www.wsdm-conference.org/2022/accepted-papers/