An Explainable Recommendation Method Based on Multi-timeslice Graph Embedding

Deep neural networks (DNN) can be used to model users’ behavior sequences and predict their interest based on the historical behavior. However, current DNN-based recommendation methods lack explainability, making them difficult to guarantee the credibility of the recommendation results. In this paper, a Multi-Timeslice Graph Embedding (MTGE) model is proposed. First, it can effectively obtain the embedded representations of user behavior (or items) on a single timeslice. Second, the dynamic evolution of user preferences can be analyzed through integrating the embedded representations on multi-timeslices. Then, an explainable recommendation algorithm based on MTGE is proposed, which can effectively improve the accuracy of recommendation and support the model-level explainability. The feasibility and effectiveness of the key technologies proposed in the paper are verified through experiments.

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

[2]  Ruslan Salakhutdinov,et al.  Probabilistic Matrix Factorization , 2007, NIPS.

[3]  Dun-Nan Liu.  Model for evaluating the electrical power system safety with hesitant fuzzy linguistic information , 2015, J. Intell. Fuzzy Syst..

[4]  Charu C. Aggarwal,et al.  Multi-dimensional Graph Convolutional Networks , 2018, SDM.

[5]  Michael R. Lyu,et al.  SoRec: social recommendation using probabilistic matrix factorization , 2008, CIKM '08.

[6]  Max Welling,et al.  Bayesian Matrix Factorization with Side Information and Dirichlet Process Mixtures , 2010, AAAI.

[7]  Lukasz Kaiser,et al.  Attention is All you Need , 2017, NIPS.

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

[9]  Martin Ester,et al.  FLAME: A Probabilistic Model Combining Aspect Based Opinion Mining and Collaborative Filtering , 2015, WSDM.

[10]  Alex Beutel,et al.  Recurrent Recommender Networks , 2017, WSDM.

[11]  Yongjun Liu,et al.  Social Network User Recommendation Method Based on Dynamic Influence , 2018, WISA.

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

[13]  Julian J. McAuley,et al.  Self-Attentive Sequential Recommendation , 2018, 2018 IEEE International Conference on Data Mining (ICDM).

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

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

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

[17]  Ed H. Chi,et al.  Towards Neural Mixture Recommender for Long Range Dependent User Sequences , 2019, WWW.

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

[19]  Wei Xu,et al.  A Graph Kernel Based Item Similarity Measure for Top-N Recommendation , 2019, WISA.