wsGAT: Weighted and Signed Graph Attention Networks for Link Prediction

TL;DR

This paper introduces wsGAT, an extension of GAT layers designed to effectively handle graphs with signed and weighted links, improving link prediction tasks in real-world networks.

Contribution

The paper presents wsGAT, a novel GNN layer that manages signed and weighted links, addressing a gap in existing GNN models for such graph types.

Findings

wsGAT outperforms GCNII and SGCN in link prediction tasks.

No performance loss when predicting signed weights.

Models with wsGAT excel on real-world signed and weighted networks.

Abstract

Graph Neural Networks (GNNs) have been widely used to learn representations on graphs and tackle many real-world problems from a wide range of domains. In this paper we propose wsGAT, an extension of the Graph Attention Network (GAT) layers, meant to address the lack of GNNs that can handle graphs with signed and weighted links, which are ubiquitous, for instance, in trust and correlation networks. We first evaluate the performance of our proposal by comparing against GCNII in the weighed link prediction task, and against SGCN in the link sign prediction task. After that, we combine the two tasks and show their performance on predicting the signed weight of links, and their existence. Our results on real-world networks show that models with wsGAT layers outperform the ones with GCNII and SGCN layers, and that there is no loss in performance when signed weights are predicted.