Two Birds with One Stone: Unified Model Learning for Both Recall and Ranking in News Recommendation

Recall and ranking are two critical steps in personalized news recommendation. Most existing news recommender systems conduct personalized news recall and ranking separately with different models. However, maintaining multiple models leads to high computational cost and poses great challenges to meeting the online latency requirement of news recommender systems. In order to handle this problem, in this paper we propose UniRec, a unified method for recall and ranking in news recommendation. In our method, we first infer user embedding for ranking from the historical news click behaviors of a user using a user encoder model. Then we derive the user embedding for recall from the obtained user embedding for ranking by using it as the attention query to select a set of basis user embeddings which encode different general user interests and synthesize them into a user embedding for recall. The extensive experiments on benchmark dataset demonstrate that our method can improve both efficiency and effectiveness for recall and ranking in news recommendation.

[1]  Tao Qi,et al.  Uni-FedRec: A Unified Privacy-Preserving News Recommendation Framework for Model Training and Online Serving , 2021, EMNLP.

[2]  Yongfeng Huang,et al.  User-as-Graph: User Modeling with Heterogeneous Graph Pooling for News Recommendation , 2021, IJCAI.

[3]  Xing Xie,et al.  HieRec: Hierarchical User Interest Modeling for Personalized News Recommendation , 2021, ACL.

[4]  Tao Qi,et al.  PP-Rec: News Recommendation with Personalized User Interest and Time-aware News Popularity , 2021, ACL.

[5]  Tao Qi,et al.  Personalized News Recommendation with Knowledge-aware Interactive Matching , 2021, SIGIR.

[6]  Chuhan Wu,et al.  FeedRec: News Feed Recommendation with Various User Feedbacks , 2021, WWW.

[7]  Xing Xie,et al.  Octopus: Comprehensive and Elastic User Representation for the Generation of Recommendation Candidates , 2020, SIGIR.

[8]  Jure Leskovec,et al.  PinnerSage: Multi-Modal User Embedding Framework for Recommendations at Pinterest , 2020, KDD.

[9]  Xing Xie,et al.  MIND: A Large-scale Dataset for News Recommendation , 2020, ACL.

[10]  User Modeling with Click Preference and Reading Satisfaction for News Recommendation , 2020, IJCAI.

[11]  Xing Xie,et al.  Fine-grained Interest Matching for Neural News Recommendation , 2020, ACL.

[12]  Suyu Ge,et al.  Graph Enhanced Representation Learning for News Recommendation , 2020, WWW.

[13]  Xing Zhao,et al.  Learning to Hash with Graph Neural Networks for Recommender Systems , 2020, WWW.

[14]  Suyu Ge,et al.  Neural News Recommendation with Multi-Head Self-Attention , 2019, EMNLP.

[15]  Xing Xie,et al.  KRED: Knowledge-Aware Document Representation for News Recommendations , 2019, RecSys.

[16]  Julian McAuley,et al.  Candidate Generation with Binary Codes for Large-Scale Top-N Recommendation , 2019, CIKM.

[17]  Xing Xie,et al.  Hi-Fi Ark: Deep User Representation via High-Fidelity Archive Network , 2019, IJCAI.

[18]  Xing Xie,et al.  NPA: Neural News Recommendation with Personalized Attention , 2019, KDD.

[19]  Xing Xie,et al.  Neural News Recommendation with Attentive Multi-View Learning , 2019, IJCAI.

[20]  Xing Xie,et al.  Neural News Recommendation with Long- and Short-term User Representations , 2019, ACL.

[21]  Xing Xie,et al.  Collaborative Metric Learning with Memory Network for Multi-Relational Recommender Systems , 2019, IJCAI.

[22]  Dietmar Jannach,et al.  News recommender systems - Survey and roads ahead , 2018, Inf. Process. Manag..

[23]  Chang Zhou,et al.  Deep Interest Evolution Network for Click-Through Rate Prediction , 2018, AAAI.

[24]  Oriol Vinyals,et al.  Representation Learning with Contrastive Predictive Coding , 2018, ArXiv.

[25]  Jure Leskovec,et al.  Graph Convolutional Neural Networks for Web-Scale Recommender Systems , 2018, KDD.

[26]  Minyi Guo,et al.  DKN: Deep Knowledge-Aware Network for News Recommendation , 2018, WWW.

[27]  Yukihiro Tagami,et al.  Embedding-based News Recommendation for Millions of Users , 2017, KDD.

[28]  Paul Covington,et al.  Deep Neural Networks for YouTube Recommendations , 2016, RecSys.

[29]  Diyi Yang,et al.  Hierarchical Attention Networks for Document Classification , 2016, NAACL.

[30]  Yury A. Malkov,et al.  Efficient and Robust Approximate Nearest Neighbor Search Using Hierarchical Navigable Small World Graphs , 2016, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[31]  Xiaodong He,et al.  A Multi-View Deep Learning Approach for Cross Domain User Modeling in Recommendation Systems , 2015, WWW.

[32]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[33]  Yoshua Bengio,et al.  Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation , 2014, EMNLP.

[34]  Larry P. Heck,et al.  Learning deep structured semantic models for web search using clickthrough data , 2013, CIKM.

[35]  Fangzhao Wu,et al.  Personalized News Recommendation: A Survey , 2021, ArXiv.

[36]  Ming-Wei Chang,et al.  BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding , 2019, NAACL.

[37]  Nitish Srivastava,et al.  Dropout: a simple way to prevent neural networks from overfitting , 2014, J. Mach. Learn. Res..