Collaborative Adversarial Learning for RelationalLearning on Multiple Bipartite Graphs

TL;DR

This paper introduces Collaborative Adversarial Learning (CAL), a novel approach that models the joint distribution of shared entities across multiple bipartite graphs to improve relational inference, especially in sparse data scenarios.

Contribution

CAL explicitly models joint distributions with distribution and feature-level alignments, enhancing knowledge transfer across multiple bipartite graphs for relational learning.

Findings

CAL outperforms existing methods on real-world datasets.

Two-level alignment improves relation inference accuracy.

Model effectively handles data sparsity in bipartite graphs.

Abstract

Relational learning aims to make relation inference by exploiting the correlations among different types of entities. Exploring relational learning on multiple bipartite graphs has been receiving attention because of its popular applications such as recommendations. How to make efficient relation inference with few observed links is the main problem on multiple bipartite graphs. Most existing approaches attempt to solve the sparsity problem via learning shared representations to integrate knowledge from multi-source data for shared entities. However, they merely model the correlations from one aspect (e.g. distribution, representation), and cannot impose sufficient constraints on different relations of the shared entities. One effective way of modeling the multi-domain data is to learn the joint distribution of the shared entities across domains.In this paper, we propose Collaborative Adversarial Learning (CAL) that explicitly models the joint distribution of the shared entities across multiple bipartite graphs. The objective of CAL is formulated from a variational lower bound that maximizes the joint log-likelihoods of the observations. In particular, CAL consists of distribution-level and feature-level alignments for knowledge from multiple bipartite graphs. The two-level alignment acts as two different constraints on different relations of the shared entities and facilitates better knowledge transfer for relational learning on multiple bipartite graphs. Extensive experiments on two real-world datasets have shown that the proposed model outperforms the existing methods.