Hierarchical Representation Learning for Bipartite Graphs

Abstract

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 embedding is decomposed into two parts, each of which captures the community-level generalizations and individualized preferences respectively. The community embedding 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.

Bipartite graph capsule network

“…Bipartite graph related neural networks Numerous research works [8,9,17,20,34,37,41] have been proposed with the focuses on the analysis of bipartite graph neural networks. Among them, [17,20,37,41] use neural networks on bipartite graphs to implement an efficient recommendation system, while [8,34] focus on cancer survival prediction and drugdisease association prediction. [9] delves into the vertex representation learning problem.…”

Polarity-based graph neural network for sign prediction in signed bipartite graphs

“…Recently, with the increasing popularity and development of network embedding [10,23] and graph neural networks (GNN) [12,16,27], methods for solving problems on bipartite graphs using neural networks continue to be proposed by numerous studies [9,19,21,28,30,34]. Amount them, [9] proposes a novel framework for cancer survival prediction, [19,21] propose novel methods to handle large-scale e-commerce tasks by analyzing the hierarchical structures and using GNNs in bipartite graphs. [34] proposes an analysis that provides insights into better extracting and fusing information from the protein-protein interaction network for drug repurposing.…”

A Review on Graph Neural Network Methods in Financial Applications

“…There are also literature using the above framework as a building block and combining clustering methodology to learn a hierarchical representation of the graph, since hierarchical representation with various GNN models could achieve satisfactory performance. For instance, Li et al (2019b) utilize the node embedding generated from the framework to cluster users into different communities and make a recommendation based on both community information and user information. Specifically, the user information is decomposed into two orthogonal spaces representing community-level information and individualized user preferences.…”