RecSys2020推荐系统论文集锦

第14届推荐人自己的年会RecSys已在9月22日到26日在线上举行。大会围绕着推荐系统相关问题进行了3场KeyNotes，5场Tutorials，接收了41篇长文，26篇短文。

通过对主题演讲以及教程的总结发现，此次大会主要聚焦在了推荐系统中的Bias问题以及对话推荐系统、对抗机器学习在推荐中的应用等。

主题演讲为以下3个：

• 4 Reasons Why Social Media Make Us Vulnerable to Manipulation. by Filippo Menczer.
• Bias in Search and Recommender Systems. by Ricardo Baeza-Yates.
• "You Really Get Me": Conversational AI Agents That Can Truly Understand and Help Users. by Michelle Zhou.

大会教程为以下6个：

• Adversarial Learning for Recommendation: Applications for Security and Generative Tasks - Concept to Code. by Vito Walter Anelli et al.
• Bayesian Value Based Recommendation: A modelling based alternative to proxy and counterfactual policy based recommendation. by David Rohde et al.
• Counteracting Bias and Increasing Fairness in Search and Recommender Systems. by Ruoyuan Gao et al.
• Introduction to Bandits in Recommender Systems. by Andrea Barraza-Urbina et al.
• Tutorial on Conversational Recommendation Systems. by Zuohui Fu et al.
• Tutorial: Feature Engineering for Recommender Systems. by Benedikt Schifferer et al.

另外，大会揭晓了今年的最佳论文奖、最佳论文提名奖、最佳短文奖。具体标题及单位如下：

• Progressive Layered Extraction (PLE): A Novel Multi-Task Learning (MTL) Model for Personalized Recommendations by H. Tang, J. Liu, M. Zhao, X. Gong (Best Long Paper)
• Exploiting Performance Estimates for Augmenting Recommendation Ensembles by G. Penha, R. L. T. Santos (Best Long Paper Runner-up)
• ADER: Adaptively Distilled Exemplar Replay Towards Continual Learning for Session-based Recommendation by F. Mi, X. Lin, B. Faltings (Best Short Paper)

最后，小编为大家收集整理了部分相关主题的论文。其中对论文的总结发现，除了以下列出的大类外，还有一些非常有意思的工作，比如对可复现性和公平对比的思考、多智能体强化学习与推荐系统的结合、对矩阵分解和神经协同过滤方法的思考等等。

一. 序列推荐

• From the lab to production: A case study of session-based recommendations in the home-improvement domain.
• ADER: Adaptively Distilled Exemplar Replay Towards Continual Learning for Session-based Recommendation.
• Exploring Longitudinal Effects of Session-based Recommendations.
• Long-tail Session-based Recommendation.
• Context-aware Graph Embedding for Session-based News Recommendation.
• Investigating the Impact of Audio States & Transitions for Track Sequencing in Music Streaming Sessions.

二. 可解释性推荐

• Explainable Recommendation for Repeat Consumption.
• Explainable Recommendations via Attentive Multi-Persona Collaborative Filtering.
• Providing Explainable Race-Time Predictions and Training Plan Recommendations to Marathon Runners.

三. 无偏的和公平的推荐

• Bias in Search and Recommender Systems
• Debiasing Item-to-Item Recommendations With Small Annotated Datasets.
• Keeping Dataset Biases out of the Simulation: A Debiased Simulator for Reinforcement Learning based Recommender Systems.
• Unbiased Ad Click Prediction for Position-aware Advertising Systems.
• Unbiased Learning for the Causal Effect of Recommendation.
• Unbiased Implicit Recommendation and Propensity Estimation via Combinational Joint Learning.
• The Connection Between Popularity Bias, Calibration, and Fairness in Recommendation.
• Counteracting Bias and Increasing Fairness in Search and Recommender Systems.
• Counteracting Bias and Increasing Fairness in Search and Recommender Systems.
• The Connection Between Popularity Bias, Calibration, and Fairness in Recommendation.
• Fairness-aware Recommendation with librec-auto.
• Ensuring Fairness in Group Recommendations by Rank-Sensitive Balancing of Relevance.

回复"RecSys2020"获取合集，更多接收的论文可以访问：https://dblp.org/db/conf/recsys/recsys2020.html