Skip to content

Latest commit

 

History

History
88 lines (68 loc) · 5.03 KB

RecSys2021.md

File metadata and controls

88 lines (68 loc) · 5.03 KB
Raw

推荐系统工业界顶会论文总结——RecSys 2021

知乎专栏

  1. Values of User Exploration in Recommender Systems
    Author(Institute): Minmin Chen(Google)
    KeyWords: reinforcement learning; exploration; serendipity; recommender systems

  2. Mitigating Confounding Bias in Recommendation via Information Bottleneck
    Author(Institute): Pengxiang Cheng(Huawei二作)
    KeyWords: bias; information bottleneck

  3. Cold Start Similar Artists Ranking with Gravity-Inspired Graph Autoencoders
    Author(Institute): GUILLAUME SALHA-GALVAN(Deezer)
    KeyWords: Music Recommendation; Music Streaming Services; Cold Start; Similar Music Artists; Ranking; Directed Graphs; Autoencoders; Variational Autoencoders; Graph Representation Learning; Node Embedding; Link Prediction
    Dataset: deezer

  4. Shared Neural Item Representations for Completely Cold Start Problem
    Author(Institute): Ramin Raziperchikolaei(Rakuten)
    KeyWords: cold start; item representations

  5. Evaluating Off-Policy Evaluation: Sensitivity and Robustness
    Author(Institute): Takuma Udagawa(Sony二作)
    KeyWords: Off-policy Evaluation
    Dataset: OptDigits; PenDigits; SatImage

  6. Towards Unified Metrics for Accuracy and Diversity for Recommender Systems
    Author(Institute): Takuma Udagawa(Sony二作)
    KeyWords: diversity; recommender systems; offline evaluation; metrics
    Dataset: Movielens

  7. Transformers4Rec: Bridging the Gap between NLP and Sequential / Session-Based Recommendation
    Author(Institute): Gabriel de Souza Pereira Moreira(NVIDIA)
    KeyWords: sequential recommendation
    Dataset: REES46 eCommerce; YOOCHOOSE eCommerce

  8. Denoising User-aware Memory Network for Recommendation
    Author(Institute): ZHI BIAN(Alibaba)
    KeyWords: Recommendation; Deep neural networks; Denoising
    Dataset: Alibaba

  9. Large-Scale Modeling of Mobile User Click Behaviors Using Deep Learning
    Author(Institute): Xin Zhou(Google)
    KeyWords: User behavior modeling; predictive user interfaces; mobile interaction; click prediction; deep learning

  10. EX3: Explainable Attribute-aware Item-set Recommendations
    Author(Institute): TONG ZHAO(Amazon二作)
    KeyWords: Recommender system; Explainable recommendation; Item set recommendation
    Dataset: Amazon

  11. Tops, Bottoms, and Shoes: Building Capsule Wardrobes via Cross-Attention Tensor Network
    Author(Institute): Huiyuan Chen(Visa)
    KeyWords: Fashion Recommendation; Neural Tensor Network; Cross-Attentionl Linear Attention
    Dataset: Polyvore; iFashion

  12. Local Factor Models for Large-Scale Inductive Recommendation
    Author(Institute): Longqi Yang(Microsoft)
    KeyWords: Recommendation; local model; large-scale; end-to-end
    Dataset: Web-35M; LastFM-17M; Movielens-10M

  13. Learning to Represent Human Motives for Goal-directed Web Browsing
    Author(Institute): Chia-Jung Lee(Amazon二作); Longqi Yang(Microsoft三作)
    KeyWords: User Behavior; User Goals; Web Browser Session Modeling; Goal Representation Learning
    Dataset: GoWeB

  14. Accordion: A Trainable Simulator for Long-Term Interactive Systems
    Author(Institute): James McInerney(Netflix);
    KeyWords: Poisson Process; Deep Learning; Simulation
    Dataset: ContentWise impressions

  15. Hierarchical Latent Relation Modeling for Collaborative Metric Learning
    Author(Institute): VIET-ANH TRAN(Deezer)
    KeyWords: Collaborative Metric Learning; Relation Modeling; Attention Mechanisms; Recommender Systems
    Dataset: MovieLens; Echonest; Yelp; Amazon book

  16. Matrix Factorization for Collaborative Filtering Is Just Solving an Adjoint Latent Dirichlet Allocation Model After All
    Author(Institute): Florian Wilhelm(inovex GmbH)
    KeyWords: Matrix factorization; Collaborative filtering

  17. Negative Interactions for Improved Collaborative-Filtering: Don’t go Deeper, go Higher
    Author(Institute): Harald Steck(Netflix);
    KeyWords: collaborative filtering; recommender systems; linear models; higher order interactions
    Dataset: ML-20M; Netflix; MSD

  18. Page-level Optimization of e-Commerce Item Recommendations
    Author(Institute): CHIEH LO(eBay)
    KeyWords: A/B testing; page-level optimization