Hierarchical Representation Learning for Bipartite Graphs

Recommender systems on E-Commerce platforms track users' online behaviors and recommend relevant items according to each user's interests and needs. Bipartite graphs that capture both user/item feature and use-item interactions have been demonstrated to be highly effective for this purpose. Recently, graph neural network (GNN) has been successfully applied in representation of bipartite graphs in industrial recommender systems. Providing individualized recommendation on a dynamic platform with billions of users is extremely challenging. A key observation is that the users of an online E-Commerce platform can be naturally clustered into a set of communities. We propose to cluster the users into a set of communities and make recommendations based on the information of the users in the community collectively. More specifically, embeddings are assigned to the communities and the user information is decomposed into two parts, each of which captures the community-level generalizations and individualized preferences respectively. The community structure can be considered as an enhancement to the GNN methods that are inherently flat and do not learn hierarchical representations of graphs. The performance of the proposed algorithm is demonstrated on a public dataset and a world-leading E-Commerce company dataset.

[1]  Daniel R. Figueiredo,et al.  struc2vec: Learning Node Representations from Structural Identity , 2017, KDD.

[2]  Fillia Makedon,et al.  Learning from Incomplete Ratings Using Non-negative Matrix Factorization , 2006, SDM.

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

[4]  Steven Skiena,et al.  HARP: Hierarchical Representation Learning for Networks , 2017, AAAI.

[5]  Gene H. Golub,et al.  Singular value decomposition and least squares solutions , 1970, Milestones in Matrix Computation.

[6]  Haibin Cheng,et al.  Real-time Personalization using Embeddings for Search Ranking at Airbnb , 2018, KDD.

[7]  Jure Leskovec,et al.  Hierarchical Graph Representation Learning with Differentiable Pooling , 2018, NeurIPS.

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

[9]  Mihajlo Grbovic,et al.  Search Ranking And Personalization at Airbnb , 2017, RecSys.

[10]  John Riedl,et al.  Collaborative Filtering Recommender Systems , 2011, Found. Trends Hum. Comput. Interact..

[11]  Jure Leskovec,et al.  node2vec: Scalable Feature Learning for Networks , 2016, KDD.

[12]  Stephan Günnemann,et al.  Deep Gaussian Embedding of Graphs: Unsupervised Inductive Learning via Ranking , 2017, ICLR.

[13]  Joan Bruna,et al.  Community Detection with Graph Neural Networks , 2017, 1705.08415.

[14]  Jure Leskovec,et al.  Predicting multicellular function through multi-layer tissue networks , 2017, Bioinform..

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

[16]  Mark Tygert,et al.  A Randomized Algorithm for Principal Component Analysis , 2008, SIAM J. Matrix Anal. Appl..

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

[18]  Ryan Moulton,et al.  Maximally Consistent Sampling and the Jaccard Index of Probability Distributions , 2018, 2018 IEEE International Conference on Data Mining Workshops (ICDMW).

[19]  Kun Gai,et al.  Learning Tree-based Deep Model for Recommender Systems , 2018, KDD.