RecSys 2020 採択論文

推薦システム分野のトップカンファレンスであるACM Recommender Systems(RecSys2020)の採択論文リストが公開されました。

昨年開催されたRecSys2019では推薦システムの再現性に関する大量の実装結果に関する論文がベストペーパーになったことでも話題になりました。RecSys自体は、レコメンデーションシステムの幅広い分野における研究成果、システム、技術を発表するための最高の国際フォーラムです。

レコメンデーションとは、過去の行動やユーザの類似性を利用して、エンドユーザの好みに合わせた情報項目のリストを生成する情報フィルタリングの一種です。RecSysは、レコメンダーシステムに取り組んでいる主要な国際的な研究グループと、世界有数のEコマース企業の多くが一堂に会することから、レコメンダーシステム研究の発表と議論の場として最も重要な年次会議となっています。

リストは公開されましたが、論文自体が公開されていないものがまだ沢山あります。順次公開に伴って更新していきます。

採択論文

Long Papers

・A Method to Anonymize Business Metrics to Publishing Implicit Feedback Datasets

・A Ranking Optimization Approach to Latent Linear Critiquing in Conversational Recommender System

・Cascading Hybrid Bandits: Online Learning to Rank for Relevance and Diversity

・Content-Collaborative Disentanglement Representation Learning for Enhanced Recommendation

・Contextual and Sequential User Embeddings for Large-Scale Music Recommendation

・Contextual User Browsing Bandits for Large-Scale Online Mobile Recommendation

・Debiasing Item-to-Item Recommendations With Small Annotated Datasets

・Deconstructing the Filter Bubble: User Decision-Making and Recommender Systems

・Doubly Robust Estimator for Ranking Metrics with Post-Click Conversions

・Ensuring Fairness in Group Recommendations by Rank-Sensitive Balancing of Relevance

・Exploiting Performance Estimates for Augmenting Recommendation Ensembles

・Exploring Clustering of Bandits for Online Recommendation System

・FISSA: Fusing Item Similarity Models with Self-Attention Networks for Sequential Recommendation

・From the Lab to Production: A Case Study of Session-Based Recommendations in the Home-Improvement Domain

・Global and Local Differential Privacy for Collaborative Bandits

・Goal-driven Command Recommendations for Analysts

・ImRec: Learning Reciprocal Preferences Using Images

・In-Store Augmented Reality-Enabled Product Comparison and Recommendation

・Keeping Dataset Biases out of the Simulation: A Debiased Simulator for Reinforcement Learning based Recommender Systems

・KRED: Knowledge-Aware Document Representation for News Recommendations

・Learning to Collaborate in Multi-Module Recommendation via Multi-Agent Reinforcement Learning without Communication

・Making Neural Networks Interpretable with Attribution: Application to Implicit Signals Prediction

・MultiRec: A Multi-Relational Approach for Unique Item Recommendation in Auction Systems

・Offline Contextual Multi-armed Bandits for Mobile Health Interventions: A Case Study on Emotion Regulation

・On Target Item Sampling in Offline Recommender System Evaluation

・Progressive Layered Extraction (PLE): A Novel Multi-Task Learning (MTL) Model for Personalized Recommendations

・PURS: Personalized Unexpected Recommender System for Improving User Satisfaction

・Recommendations as Graph Explorations

・Recommending the Video to Watch Next: An Offline and Online Evaluation at YOUTV.de

・RecSeats: A Hybrid Convolutional Neural Network Choice Model for Seat Recommendations at Reserved Seating Venues

・Revisiting Adversarially Learned Injection Attacks Against Recommender Systems

・SSE-PT: Sequential Recommendation Via Personalized Transformer

・TAFA: Two-headed Attention Fused Autoencoder for Context-Aware Recommendations

・Theoretical Modeling of the Iterative Properties of User Discovery in a Collaborative Filtering Recommender System

・Towards Safety and Sustainability: Designing Local Recommendations for Post-pandemic World

・Unbiased Ad Click Prediction for Position-aware Advertising Systems

・Unbiased Learning for the Causal Effect of Recommendation

・What does BERT know about books, movies and music? Probing BERT for Conversational Recommendation

・Who Doesn’t Like Dinosaurs? Finding and Eliciting Richer Preferences for Recommendation

Short Papers

・Adaptive Pointwise-Pairwise Learning-to-Rank for Content-based Personalized Recommendation

・ADER: Adaptively Distilled Exemplar Replay Towards Continual Learning for Session-based Recommendation

・Carousel Personalization in Music Streaming Apps with Contextual Bandits

・Causal Inference on Recommender Systems

・ClusterExplorer: Enable User Control over Related Recommendations via Collaborative Filtering and Clustering

・Combining Rating and Review Data by Initializing Latent Factor Models with Topic Models for Top-N Recommendation

・Contextual Meta-Bandit for Recommender Systems Selection

・Deconfounding User Satisfaction Estimation from Response Rate Bias

・Deep Bayesian Bandits: Exploring in Online Personalized Recommendations

・Explainable Recommendation for Repeat Consumption

・Explainable Recommendations via Attentive Multi-Persona Collaborative Filtering

・Exploring Longitudinal Effects of Session-based Recommendations

・Fit to Run: Personalised Recommendations for Marathon Training

・Free Lunch! Retrospective Uplift Modeling for Dynamic Promotions Recommendation within ROI Constraints

・History-Augmented Collaborative Filtering for Financial Recommendations

・Improving One-class Recommendation with Multi-tasking on Various Preference Intensities

・Interpretable Contextual Team-aware Item Recommendation: Application in Multiplayer Online Battle Arena Games

・Long-tail Session-based Recommendation

・MEANTIME: Mixture of Attention Mechanisms with Multi-temporal Embeddings for Sequential Recommendation

・Model Size Reduction Using Frequency Based Double Hashing for Recommender Systems

・Performance of Hyperbolic Geometry Models in Top-N Recommendation Tasks

・Personality Bias of Music Recommendation Algorithms

・Providing Explainable Race-Time Predictions and Training Plan Recommendations to Marathon Runners

・Reducing Energy Waste in Households Through Real-Time Recommendations

・Unbiased Implicit Recommendation and Propensity Estimation via Combinational Joint Learning

・Using Conceptual Incongruity as a Basis for Making Recommendations

 

今回のRecSys単独著者の齋藤 優太様にも発表していただく予定です。

 

• 
• 
• 

この記事に関するカテゴリー

• 論文