CoupledCF: Learning Explicit and Implicit User-item Couplings in Recommendation for Deep Collaborative Filtering

Non-IID recommender system discloses the nature of recommendation and has shown its potential in improving recommendation quality and addressing issues such as sparsity and cold start. It leverages existing work that usually treats users/items as independent while ignoring the rich couplings within and between users and items, leading to limited performance improvement. In reality, users/items are related with various couplings existing within and between users and items, which may better explain how and why a user has personalized preference on an item. This work builds on non-IID learning to propose a neural user-item coupling learning for collaborative filtering, called CoupledCF. CoupledCF jointly learns explicit and implicit couplings within/between users and items w.r.t. user/item attributes and deep features for deep CF recommendation. Empirical results on two real-world large datasets show that CoupledCF significantly outperforms two latest neural recommenders: neural matrix factorization and Google's Wide & Deep network.

[1]  Fangfang Li,et al.  CGMF: Coupled Group-Based Matrix Factorization for Recommender System , 2013, WISE.

[2]  Longbing Cao,et al.  Coupling learning of complex interactions , 2015, Inf. Process. Manag..

[3]  Martha Larson,et al.  Collaborative Filtering beyond the User-Item Matrix , 2014, ACM Comput. Surv..

[4]  Longbing Cao,et al.  Formalization and Verification of Group Behavior Interactions , 2015, IEEE Transactions on Systems, Man, and Cybernetics: Systems.

[5]  Jeffrey Dean,et al.  Efficient Estimation of Word Representations in Vector Space , 2013, ICLR.

[6]  Donghyun Kim,et al.  Convolutional Matrix Factorization for Document Context-Aware Recommendation , 2016, RecSys.

[7]  Longbing Cao,et al.  Document similarity analysis via involving both explicit and implicit semantic couplings , 2015, 2015 IEEE International Conference on Data Science and Advanced Analytics (DSAA).

[8]  Li Chen,et al.  Group Bayesian personalized ranking with rich interactions for one-class collaborative filtering , 2016, Neurocomputing.

[9]  Dit-Yan Yeung,et al.  Collaborative Deep Learning for Recommender Systems , 2014, KDD.

[10]  Xiangnan He,et al.  A Generic Coordinate Descent Framework for Learning from Implicit Feedback , 2016, WWW.

[11]  ChengXiang Zhai,et al.  Exploiting rich user information for one-class collaborative filtering , 2012, Knowledge and Information Systems.

[12]  Heng-Tze Cheng,et al.  Wide & Deep Learning for Recommender Systems , 2016, DLRS@RecSys.

[13]  Longbing Cao,et al.  Attention-Based Transactional Context Embedding for Next-Item Recommendation , 2018, AAAI.

[14]  Lynda L. McGhie,et al.  World Wide Web , 2011, Encyclopedia of Information Assurance.

[15]  Yang Gao,et al.  A Coupled Clustering Approach for Items Recommendation , 2013, PAKDD.

[16]  Min Xiao,et al.  Predictive Collaborative Filtering with Side Information , 2016, IJCAI.

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

[18]  Kai Lu,et al.  Metric-Based Auto-Instructor for Learning Mixed Data Representation , 2018, AAAI.

[19]  正好 長谷川 Information Processing and Management:[8]Patent Information , 1984 .

[20]  Longbing Cao,et al.  Coupled Poisson Factorization Integrated With User/Item Metadata for Modeling Popular and Sparse Ratings in Scalable Recommendation , 2018, AAAI.

[21]  Yunming Ye,et al.  DeepFM: A Factorization-Machine based Neural Network for CTR Prediction , 2017, IJCAI.

[22]  Qiang Liu,et al.  Heterogeneous Metric Learning of Categorical Data with Hierarchical Couplings , 2018, IEEE Transactions on Knowledge and Data Engineering.

[23]  James Parker,et al.  on Knowledge and Data Engineering, , 1990 .

[24]  Longbing Cao,et al.  Non-IIDness Learning in Behavioral and Social Data , 2014, Comput. J..

[25]  Philip S. Yu,et al.  Coupled Behavior Analysis with Applications , 2012, IEEE Transactions on Knowledge and Data Engineering.

[26]  Fangfang Li,et al.  Coupled Matrix Factorization Within Non-IID Context , 2014, PAKDD.

[27]  C. Q. Lee,et al.  The Computer Journal , 1958, Nature.

[28]  Yanchun Zhang,et al.  A Graph-based model for context-aware recommendation using implicit feedback data , 2015, World Wide Web.

[29]  Preslav Nakov,et al.  A non-IID Framework for Collaborative Filtering with Restricted Boltzmann Machines , 2013, ICML.

[30]  Ling Chen,et al.  Outlier Detection in Complex Categorical Data by Modeling the Feature Value Couplings , 2016, IJCAI.

[31]  Longbing Cao,et al.  Non-IID Recommender Systems: A Review and Framework of Recommendation Paradigm Shifting , 2016, ArXiv.

[32]  Sunho Park,et al.  Hierarchical Bayesian Matrix Factorization with Side Information , 2013, IJCAI.

[33]  F. Maxwell Harper,et al.  The MovieLens Datasets: History and Context , 2016, TIIS.