Effective and Lightweight Representation Learning for Link Sign Prediction in Signed Bipartite Graphs

TL;DR

ELISE is a lightweight, efficient GNN-based method that improves link sign prediction in signed bipartite graphs by extending personalized propagation and using low-rank approximation, avoiding over-smoothing and reducing noise.

Contribution

The paper introduces ELISE, a novel approach that enhances signed bipartite graph learning by integrating signed edges into personalized propagation and employing low-rank approximation for efficiency and effectiveness.

Findings

ELISE outperforms existing methods in link sign prediction accuracy.

ELISE achieves faster training and inference times.

ELISE effectively mitigates over-smoothing and noise issues in signed bipartite graphs.

Abstract

How can we effectively and efficiently learn node representations in signed bipartite graphs? A signed bipartite graph is a graph consisting of two nodes sets where nodes of different types are positively or negative connected, and it has been extensively used to model various real-world relationships such as e-commerce, etc. To analyze such a graph, previous studies have focused on designing methods for learning node representations using graph neural networks. In particular, these methods insert edges between nodes of the same type based on balance theory, enabling them to leverage augmented structures in their learning. However, the existing methods rely on a naive message passing design, which is prone to over-smoothing and susceptible to noisy interactions in real-world graphs. Furthermore, they suffer from computational inefficiency due to their heavy design and the significant increase in the number of added edges. In this paper, we propose ELISE, an effective and lightweight GNN-based approach for learning signed bipartite graphs. We first extend personalized propagation to a signed bipartite graph, incorporating signed edges during message passing. This extension adheres to balance theory without introducing additional edges, mitigating the over-smoothing issue and enhancing representation power. We then jointly learn node embeddings on a low-rank approximation of the signed bipartite graph, which reduces potential noise and emphasizes its global structure, further improving expressiveness without significant loss of efficiency. We encapsulate these ideas into ELISE, designing it to be lightweight, unlike the previous methods that add too many edges and cause inefficiency. Through extensive experiments on real-world signed bipartite graphs, we demonstrate that ELISE outperforms its competitors for predicting link signs while providing faster training and inference time.