Dual Interests-Aligned Graph Auto-Encoders for Cross-domain Recommendation in WeChat

Recently, cross-domain recommendation (CDR) has been widely studied in both research and industry since it can alleviate a long-standing challenge of traditional recommendation methods, i.e., data sparsity issue, by transferring the information from a relatively richer domain (termed source domain) to a sparser domain (termed target domain). To our best knowledge, most (if not all) existing CDR methods focus on transferring either the similar content information or the user preferences embedding from the source domain to the target domain. However, they fail to improve the recommendation performance in real-world recommendation scenarios where the items in the source domain are totally different from those in the target domain in terms of attributes. To solve the above issues, we analyzed the historical interactions of users from different domains in the WeChat platform, and found that if two users have similar interests (interactions) in one domain, they are very likely to have similar interests in another domain even though the items of these two domains are totally different in terms of attributes. Based on this observation, in this paper, we propose a novel model named Dual Interests-Aligned Graph Auto-Encoders (DIAGAE) by utilizing the inter-domain interest alignment of users. Besides, our proposed model DIAGAE also leverages graph decoding objectives to align intra-domain user interests, which makes the representation of two users who have similar interests in a single domain closer. Comprehensive experimental results demonstrate that our model DIAGAE outperforms state-of-the-art methods on both public benchmark datasets and online A/B tests in WeChat live-stream recommendation scenario. Our model DIAGAE now serves the major online traffic in WeChat live-streaming recommendation scenario.

[1]  Kam-Fai Wong,et al.  Quotation Recommendation for Multi-party Online Conversations Based on Semantic and Topic Fusion , 2023, ACM Trans. Inf. Syst..

[2]  Depeng Jin,et al.  Robust Preference-Guided Denoising for Graph based Social Recommendation , 2023, WWW.

[3]  Shijie Sun,et al.  PlatoGL: Effective and Scalable Deep Graph Learning System for Graph-enhanced Real-Time Recommendation , 2022, CIKM.

[4]  Tingwen Liu,et al.  DisenCDR: Learning Disentangled Representations for Cross-Domain Recommendation , 2022, SIGIR.

[5]  M. Zhang,et al.  A Survey on the Fairness of Recommender Systems , 2022, ACM Trans. Inf. Syst..

[6]  Ruiming Tang,et al.  Content Filtering Enriched GNN Framework for News Recommendation , 2021, ArXiv.

[7]  Fuzhen Zhuang,et al.  Personalized Transfer of User Preferences for Cross-domain Recommendation , 2021, WSDM.

[8]  Xiangnan He,et al.  A Survey of Graph Neural Networks for Recommender Systems: Challenges, Methods, and Directions , 2021, Trans. Recomm. Syst..

[9]  Qianli Ma,et al.  Multi-view Denoising Graph Auto-Encoders on Heterogeneous Information Networks for Cold-start Recommendation , 2021, KDD.

[10]  Fuzhen Zhuang,et al.  Transfer-Meta Framework for Cross-domain Recommendation to Cold-Start Users , 2021, SIGIR.

[11]  Guanfeng Liu,et al.  Cross-Domain Recommendation: Challenges, Progress, and Prospects , 2021, IJCAI.

[12]  Meng Liu,et al.  Cross Domain Recommendation via Bi-directional Transfer Graph Collaborative Filtering Networks , 2020, CIKM.

[13]  I. Tsang,et al.  Towards Equivalent Transformation of User Preferences in Cross Domain Recommendation , 2020, ArXiv.

[14]  Yan Wang,et al.  A Graphical and Attentional Framework for Dual-Target Cross-Domain Recommendation , 2020, IJCAI.

[15]  Zhihua Cui,et al.  Personalized Recommendation System Based on Collaborative Filtering for IoT Scenarios , 2020, IEEE Transactions on Services Computing.

[16]  Hongbo Deng,et al.  CATN: Cross-Domain Recommendation for Cold-Start Users via Aspect Transfer Network , 2020, SIGIR.

[17]  Ed H. Chi,et al.  Mixed Negative Sampling for Learning Two-tower Neural Networks in Recommendations , 2020, WWW.

[18]  Dongha Lee,et al.  Semi-Supervised Learning for Cross-Domain Recommendation to Cold-Start Users , 2019, CIKM.

[19]  Xiangnan He,et al.  MMGCN: Multi-modal Graph Convolution Network for Personalized Recommendation of Micro-video , 2019, ACM Multimedia.

[20]  Pan Li,et al.  DDTCDR: Deep Dual Transfer Cross Domain Recommendation , 2019, WSDM.

[21]  Li Wei,et al.  Recommending what video to watch next: a multitask ranking system , 2019, RecSys.

[22]  Depeng Jin,et al.  Reinforced Negative Sampling for Recommendation with Exposure Data , 2019, IJCAI.

[23]  Xiaofei Zhou,et al.  DAN: Deep Attention Neural Network for News Recommendation , 2019, AAAI.

[24]  Yang Xu,et al.  Deeply Fusing Reviews and Contents for Cold Start Users in Cross-Domain Recommendation Systems , 2019, AAAI.

[25]  Lina Yao,et al.  DARec: Deep Domain Adaptation for Cross-Domain Recommendation via Transferring Rating Patterns , 2019, IJCAI.

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

[27]  Kai Zhao,et al.  Cross-domain Recommendation Without Sharing User-relevant Data , 2019, WWW.

[28]  Yanfang Ye,et al.  Heterogeneous Graph Attention Network , 2019, WWW.

[29]  Ed H. Chi,et al.  Top-K Off-Policy Correction for a REINFORCE Recommender System , 2018, WSDM.

[30]  Yu Zhang,et al.  CoNet: Collaborative Cross Networks for Cross-Domain Recommendation , 2018, UMCit@KDD.

[31]  Philip S. Yu,et al.  Heterogeneous Information Network Embedding for Recommendation , 2017, IEEE Transactions on Knowledge and Data Engineering.

[32]  Pietro Liò,et al.  Graph Attention Networks , 2017, ICLR.

[33]  Xiaolong Jin,et al.  Cross-Domain Recommendation: An Embedding and Mapping Approach , 2017, IJCAI.

[34]  Shujian Huang,et al.  Deep Matrix Factorization Models for Recommender Systems , 2017, IJCAI.

[35]  Chun Chen,et al.  Cross domain recommendation based on multi-type media fusion , 2014, Neurocomputing.

[36]  Rong Hu,et al.  Enhancing collaborative filtering systems with personality information , 2011, RecSys '11.

[37]  Don Towsley,et al.  Empirical analysis of the evolution of follower network: A case study on Douban , 2011, 2011 IEEE Conference on Computer Communications Workshops (INFOCOM WKSHPS).

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

[39]  R. Real,et al.  AUC: a misleading measure of the performance of predictive distribution models , 2008 .

[40]  Rianne van den Berg,et al.  Graph Convolutional Matrix Completion , 2017, ArXiv.

[41]  Iván Cantador,et al.  Exploiting Social Tags in Matrix Factorization Models for Cross-domain Collaborative Filtering , 2014, CBRecSys@RecSys.

[42]  Geoffrey E. Hinton,et al.  Visualizing Data using t-SNE , 2008 .

[43]  Jonathan L. Herlocker,et al.  Evaluating collaborative filtering recommender systems , 2004, TOIS.