Learning Disentangled Representations in Signed Directed Graphs without Social Assumptions

TL;DR

This paper introduces DINES, a novel method for learning disentangled node representations in signed directed graphs that does not rely on social assumptions, improving sign prediction accuracy by capturing multiple latent factors.

Contribution

DINES is the first approach to learn disentangled representations in signed directed graphs without social assumptions, using lightweight convolutions and a self-supervised discriminator.

Findings

DINES outperforms existing methods in sign prediction tasks.

Disentangled representations improve interpretability of signed relationships.

The method effectively captures multiple latent factors influencing relationships.

Abstract

Signed graphs are complex systems that represent trust relationships or preferences in various domains. Learning node representations in such graphs is crucial for many mining tasks. Although real-world signed relationships can be influenced by multiple latent factors, most existing methods often oversimplify the modeling of signed relationships by relying on social theories and treating them as simplistic factors. This limits their expressiveness and their ability to capture the diverse factors that shape these relationships. In this paper, we propose DINES, a novel method for learning disentangled node representations in signed directed graphs without social assumptions. We adopt a disentangled framework that separates each embedding into distinct factors, allowing for capturing multiple latent factors. We also explore lightweight graph convolutions that focus solely on sign and direction, without depending on social theories. Additionally, we propose a decoder that effectively classifies an edge's sign by considering correlations between the factors. To further enhance disentanglement, we jointly train a self-supervised factor discriminator with our encoder and decoder. Throughout extensive experiments on real-world signed directed graphs, we show that DINES effectively learns disentangled node representations, and significantly outperforms its competitors in the sign prediction task.