Skip to content

Latest commit

 

History

History
199 lines (156 loc) · 10.6 KB

SIGIR2021.md

File metadata and controls

199 lines (156 loc) · 10.6 KB
Raw

推荐系统工业界顶会论文总结——AAAI 2021

知乎专栏

  1. Looking at CTR Prediction Again: Is Attention All You Need?
    Author(Institute): Yuan Cheng(BOSSZhipin)
    KeyWords: click-through rate prediction; neural networks; self-attention mechanism; factorization machines; discrete choice model
    Dataset: Criteo; Avazu

  2. Mix Cache-based Distributed Training System for CTR Models with Huge Embedding Table
    Author(Institute): Huifeng Guo(Huawei)
    KeyWords: CTR Prediction; Recommendation; Distributed Training System
    Dataset: Criteo-TB

  3. A General Method For Automatic Discovery of Powerful Interactions In Click-Through Rate Prediction
    Author(Institute): Yumeng Li(Alibaba三作)
    KeyWords: Click-through Rate Prediction; Gradient-based Neural Architecture Search; Feature Interaction; Interaction Ensemble
    Dataset: Criteo; Avazu; Movielens; Frappe

  4. Learning Graph Meta Embeddings for Cold-Start Ads in Click-Through Rate Prediction
    Author(Institute): Yumeng Li(Alibaba)
    KeyWords: Online advertising; CTR prediction; Cold start; Deep learning
    Dataset: ML-1M; Taobao; News feed

  5. GemNN: Gating-enhanced Multi-task Neural Networks with Feature Interaction Learning for CTR Prediction
    Author(Institute): Hongliang Fei(Baidu)
    KeyWords: CTR

  6. Deep User Match Network for Click-Through Rate Prediction
    Author(Institute): Zai Huang(Alibaba)
    KeyWords: CTR

  7. RLNF: Reinforcement Learning based Noise Filtering for Click-Through Rate Prediction
    Author(Institute): Pu Zhao(Microsoft)
    KeyWords: CTR
    Dataset: Avazu

  8. Category-aware Collaborative Sequential Recommendation
    Author(Institute): Chong Wang(Bytedance四作)
    KeyWords: Sequential recommendation

  9. Learning to Ask Appropriate Questions in Conversational Recommendation
    Author(Institute): Hao Wang(Alibaba四作)
    KeyWords: Conversational recommender systems; knowledge graph; clarifying question; preference mining
    Dataset: MovieLens-1M; DBbook2014

  10. Personalized News Recommendation with Knowledge-aware Interactive Matching
    Author(Institute): Fangzhao Wu(Microsoft二作)
    KeyWords: News Recommendation; Interactive Matching; Single-Tower
    Dataset: MIND; Feeds

  11. Empowering News Recommendation with Pre-trained Language Models
    Author(Institute): Fangzhao Wu(Microsoft二作)
    KeyWords: News Recommendation; pre-trained language model
    Dataset: MIND; Multilingual

  12. Graph Meta Network for Multi-Behavior Recommendation
    Author(Institute): Chao Huang(JD三作)
    KeyWords: Multi-Behavior Recommendation
    Dataset: Taobao-Data; Beibei-Data; IJCAI-Contest

  13. AutoDebias: Learning to Debias for Recommendation
    Author(Institute): Guli Lin(Alibaba四作)
    KeyWords: Recommendation; Bias; Debias; Meta-learning
    Dataset: Yahoo!R3; Coat; Simulation

  14. Causal Intervention for Leveraging Popularity Bias in Recommendation
    Author(Institute): Chonggang Song(Tencent三作)
    KeyWords: Popularity Bias; Causal Intervention
    Dataset: Kwai; Douban Movie; Tencent

  15. Counterfactual Reward Modification for Streaming Recommendation with Delayed Feedback
    Author(Institute): Hanjing Su(Tencent三作)
    KeyWords: Streaming Recommendation
    Dataset: WeChat

  16. Package Recommendation with Intra- and Inter-Package Attention Networks
    Author(Institute): Chen Li(WeChat)
    KeyWords: Package Recommendation; Attention

  17. Lighter and Better: Low-Rank Decomposed Self-Attention Networks for Next-Item Recommendation
    Author(Institute): Zheng Liu(Microsoft三作)
    KeyWords: Low-Rank Self-Attention; Next-Item Recommendation
    Dataset: Yelp; Books; ML-1M

  18. Unified Conversational Recommendation Policy Learning via Graph-based Reinforcement Learning
    Author(Institute): Yaliang Li(Alibaba二作)
    KeyWords: Conversational Recommendation; Reinforcement Learning; Graph Representation Learning
    Dataset: LastFM; Yelp; Taobao

  19. Joint Knowledge Pruning and Recurrent Graph Convolution for News Recommendation
    Author(Institute): Fangzhao Wu(Microsoft四作)
    KeyWords: Recurrent Graph Convolution; Knowledge Pruning; News Recommendation
    Dataset: MIND; Adressa

  20. AMM: Attentive Multi-field Matching for News Recommendation
    Author(Institute): Qi Zhang(Huawei)
    KeyWords: News Recommendation

  21. RMBERT: News Recommendation via Recurrent Reasoning Memory Network over BERT
    Author(Institute): Qinglin Jia(Huawei)
    KeyWords: news recommendation; BERT

  22. FedCT: Federated Collaborative Transfer for Recommendation
    Author(Institute): Wenhui Yu(Alibaba三作)
    KeyWords: Federated Collaborative Transfer

  23. Transfer-Meta Framework for Cross-domain Recommendation to Cold-Start Users
    Author(Institute): Yongchun Zhu(WeChat三作)
    KeyWords: Cross-domain Recommendation; Meta Learning; Cold-start Dataset: Amazon; Douban

  24. Structured Graph Convolutional Networks with Stochastic Masks for Recommender Systems
    Author(Institute): Huiyuan Chen(Visa)
    KeyWords: Structured Graph Convolutional Networks

  25. Self-supervised Graph Learning for Recommendation
    Author(Institute): Jianxun Lian(Microsoft四作)
    KeyWords: Collaborative filtering; Graph Neural Network; Self-supervised Learning; Long-tail Recommendation
    Dataset: Yelp2018; Amazon-Book; Alibaba-iFashion

  26. Learning Recommender Systems with Implicit Feedback via Soft Target Enhancement
    Author(Institute): Fajie Yuan(Tencent二作)
    KeyWords: Soft Target Enhancement

  27. PreSizE: Predicting Size in E-Commerce using Transformers
    Author(Institute): Yotam Eshel(eBay)
    KeyWords: Size Prediction; Transformers; Deep-Learning
    Dataset: eBay

  28. Did you buy it already? Detecting Users Purchase-State From Their Product-Related Questions
    Author(Institute): Lital Kuchy(Amazon)
    KeyWords: Purchase state classification; Product question answering
    Dataset: Amazon

  29. Path-based Deep Network for Candidate Item Matching in Recommenders
    Author(Institute): Houyi Li(Alibaba)
    KeyWords: Deep Learning; Recommendation Systems
    Dataset: MovieLens; Pinterest; Amazon Books

  30. How Powerful are Interest Diffusion on Purchasing Prediction: A Case Study of Taocode Author(Institute): Shen Fa(Alibaba二作)
    KeyWords: purchasing prediction; information diffusion; GNN; Taocode
    Dataset: Taocode

  31. Enhanced Doubly Robust Learning for Debiasing Post-Click Conversion Rate Estimation
    Author(Institute): Lixin Zou(Baidu二作)
    KeyWords: Selection Bias; Missing-Not-At-Random Data; Doubly Robust; Postclick Conversion Rate Estimation
    Dataset: MovieLens

  32. On Interpretation and Measurement of Soft Attributes for Recommendation
    Author(Institute): Filip Radlinski(Google二作)
    KeyWords: Soft attributes; Recommendation critiquing; Preference feedback
    Dataset: MovieLens

  33. Learning to Warm Up Cold Item Embeddings for Cold-start Recommendation with Meta Scaling and Shifting Networks
    Author(Institute): Ruobing Xie(WeChat三作)
    KeyWords: Cold-start Recommendation; Item ID Embedding; Warm Up; Meta Network
    Dataset: MovieLens-1M; Taobao Display Ad Click; CIKM2019 EComm AI

  34. Fairness among New Items in Cold Start Recommender Systems
    Author(Institute): Jingu Kim(Netflix二作)
    KeyWords: fairness; cold start recommendation
    Dataset: ML1M; ML20M; CiteULike; XING

  35. Long-Tail Hashing
    Author(Institute): Yuqing Hou(Meituan三作)
    KeyWords: learning to hash; long-tail datasets; memory network; large-scale multimedia retrieval
    Dataset: Cifar100; ImageNet100

  36. Neural Representations in Hybrid Recommender Systems: Prediction versus Regularization
    Author(Institute): Ramin Raziperchikolaei(Rakuten)
    KeyWords: hybrid recommender systems; neural networks; regularization
    Dataset: ml100k; ml1m; Ichiba

  37. Cross-Batch Negative Sampling for Training Two-Tower Recommenders
    Author(Institute): Jieming Zhu(Huawei二作)
    KeyWords: Recommender systems; information retrieval; neural networks
    Dataset: Amazon

  38. Explicit Semantic Cross Feature Learning via Pre-trained Graph Neural Networks for CTR Prediction
    Author(Institute): Feng Li(Alibaba)
    KeyWords: CTR prediction; Pre-trained GNNs; Cross Features; Explicit Fashion
    Dataset: MovieLens

  39. Underestimation Refinement: A General Enhancement Strategy for Exploration in Recommendation Systems
    Author(Institute): Yuhai Song(JD)
    KeyWords: Contextual Bandit
    Dataset: Yahoo

  40. StackRec: Efficient Training of Very Deep Sequential Recommender Models by Iterative Stacking
    Author(Institute): Fajie Yuan(Tencent三作)
    KeyWords: Knowledge Transfer; Training acceleration
    Dataset: ML20; Kuaibao; ColdRec

  41. FORM: Follow the Online Regularized Meta-Leader for Cold-Start Recommendation
    Author(Institute): Yanrong Kang(Tencent四作)
    KeyWords: Meta-learning