Multi-behavior Recommendation with Graph Convolutional Networks

Traditional recommendation models that usually utilize only one type of user-item interaction are faced with serious data sparsity or cold start issues. Multi-behavior recommendation taking use of multiple types of user-item interactions, such as clicks and favorites, can serve as an effective solution. Early efforts towards multi-behavior recommendation fail to capture behaviors' different influence strength on target behavior. They also ignore behaviors' semantics which is implied in multi-behavior data. Both of these two limitations make the data not fully exploited for improving the recommendation performance on the target behavior. In this work, we approach this problem by innovatively constructing a unified graph to represent multi-behavior data and proposing a new model named MBGCN (short for Multi-Behavior Graph Convolutional Network ). Learning behavior strength by user-item propagation layer and capturing behavior semantics by item-item propagation layer, MBGCN can well address the limitations of existing works. Empirical results on two real-world datasets verify the effectiveness of our model in exploiting multi-behavior data. Our model outperforms the best baseline by 25.02% and 6.51% averagely on two datasets. Further studies on cold-start users confirm the practicability of our proposed model.

[1]  Max Welling,et al.  Semi-Supervised Classification with Graph Convolutional Networks , 2016, ICLR.

[2]  George Karypis,et al.  SLIM: Sparse Linear Methods for Top-N Recommender Systems , 2011, 2011 IEEE 11th International Conference on Data Mining.

[3]  Mohan S. Kankanhalli,et al.  A^3NCF: An Adaptive Aspect Attention Model for Rating Prediction , 2018, IJCAI.

[4]  Marco Gori,et al.  ItemRank: A Random-Walk Based Scoring Algorithm for Recommender Engines , 2007, IJCAI.

[5]  Martha Larson,et al.  Bayesian Personalized Ranking with Multi-Channel User Feedback , 2016, RecSys.

[6]  Yi-Hsuan Yang,et al.  Collaborative Similarity Embedding for Recommender Systems , 2019, WWW.

[7]  Yiqun Liu,et al.  Efficient Non-Sampling Factorization Machines for Optimal Context-Aware Recommendation , 2020, WWW.

[8]  Hao Wang,et al.  Exploiting POI-Specific Geographical Influence for Point-of-Interest Recommendation , 2018, IJCAI.

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

[10]  Jure Leskovec,et al.  Inductive Representation Learning on Large Graphs , 2017, NIPS.

[11]  Max Welling,et al.  Graph Convolutional Matrix Completion , 2017, ArXiv.

[12]  John Riedl,et al.  Item-based collaborative filtering recommendation algorithms , 2001, WWW '01.

[13]  Yuan He,et al.  Graph Neural Networks for Social Recommendation , 2019, WWW.

[14]  Yehuda Koren,et al.  Matrix Factorization Techniques for Recommender Systems , 2009, Computer.

[15]  Steven Skiena,et al.  DeepWalk: online learning of social representations , 2014, KDD.

[16]  Geoffrey J. Gordon,et al.  Relational learning via collective matrix factorization , 2008, KDD.

[17]  Yehuda Koren,et al.  Factorization meets the neighborhood: a multifaceted collaborative filtering model , 2008, KDD.

[18]  Tat-Seng Chua,et al.  Neural Graph Collaborative Filtering , 2019, SIGIR.

[19]  Chuan-Ju Wang,et al.  HOP-rec: high-order proximity for implicit recommendation , 2018, RecSys.

[20]  Chen Gao,et al.  Learning to Recommend With Multiple Cascading Behaviors , 2018, IEEE Transactions on Knowledge and Data Engineering.

[21]  Chen Gao,et al.  Price-aware Recommendation with Graph Convolutional Networks , 2020, 2020 IEEE 36th International Conference on Data Engineering (ICDE).

[22]  Xing Xie,et al.  Session-based Recommendation with Graph Neural Networks , 2018, AAAI.

[23]  Lars Schmidt-Thieme,et al.  BPR: Bayesian Personalized Ranking from Implicit Feedback , 2009, UAI.

[24]  George Karypis,et al.  FISM: factored item similarity models for top-N recommender systems , 2013, KDD.

[25]  Yoshua Bengio,et al.  Understanding the difficulty of training deep feedforward neural networks , 2010, AISTATS.

[26]  Lior Rokach,et al.  Introduction to Recommender Systems Handbook , 2011, Recommender Systems Handbook.

[27]  Yi-Hsuan Yang,et al.  Query-based Music Recommendations via Preference Embedding , 2016, RecSys.

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

[29]  Shankar Kumar,et al.  Video suggestion and discovery for youtube: taking random walks through the view graph , 2008, WWW.

[30]  Rajeev Motwani,et al.  The PageRank Citation Ranking : Bringing Order to the Web , 1999, WWW 1999.

[31]  Yongdong Zhang,et al.  LightGCN: Simplifying and Powering Graph Convolution Network for Recommendation , 2020, SIGIR.

[32]  Jure Leskovec,et al.  How Powerful are Graph Neural Networks? , 2018, ICLR.

[33]  Jure Leskovec,et al.  Pixie: A System for Recommending 3+ Billion Items to 200+ Million Users in Real-Time , 2017, WWW.

[34]  Kilian Q. Weinberger,et al.  Simplifying Graph Convolutional Networks , 2019, ICML.

[35]  Yiqun Liu,et al.  Efficient Heterogeneous Collaborative Filtering without Negative Sampling for Recommendation , 2020, AAAI.

[36]  Max Welling,et al.  Modeling Relational Data with Graph Convolutional Networks , 2017, ESWC.

[37]  Tat-Seng Chua,et al.  Fast Matrix Factorization for Online Recommendation with Implicit Feedback , 2016, SIGIR.

[38]  Yun Liu,et al.  BPRH: Bayesian personalized ranking for heterogeneous implicit feedback , 2018, Inf. Sci..

[39]  Yixin Cao,et al.  KGAT: Knowledge Graph Attention Network for Recommendation , 2019, KDD.

[40]  Tat-Seng Chua,et al.  Neural Collaborative Filtering , 2017, WWW.

[41]  Tat-Seng Chua,et al.  Improving Implicit Recommender Systems with View Data , 2018, IJCAI.

[42]  Liang Tang,et al.  An Empirical Study on Recommendation with Multiple Types of Feedback , 2016, KDD.

[43]  Mingzhe Wang,et al.  LINE: Large-scale Information Network Embedding , 2015, WWW.