Toward Robust Signed Graph Learning through Joint Input-Target Denoising

TL;DR

This paper introduces RIDGE, a novel framework that enhances the robustness of Signed Graph Neural Networks by jointly denoising input data and supervision targets, extending graph information bottleneck theory.

Contribution

The paper proposes a new robust signed graph learning method, RIDGE, which incorporates target space denoising guided by extended GIB theory, addressing noise in both input and supervision signals.

Findings

RIDGE improves robustness of SGNNs under various noise levels.

Experimental validation on four datasets shows significant performance gains.

RIDGE effectively denoises both input data and supervision targets.

Abstract

Signed Graph Neural Networks (SGNNs) are widely adopted to analyze complex patterns in signed graphs with both positive and negative links. Given the noisy nature of real-world connections, the robustness of SGNN has also emerged as a pivotal research area. Under the supervision of empirical properties, graph structure learning has shown its robustness on signed graph representation learning, however, there remains a paucity of research investigating a robust SGNN with theoretical guidance. Inspired by the success of graph information bottleneck (GIB) in information extraction, we propose RIDGE, a novel framework for Robust sI gned graph learning through joint Denoising of Graph inputs and supervision targEts. Different from the basic GIB, we extend the GIB theory with the capability of target space denoising as the co-existence of noise in both input and target spaces. In instantiation, RIDGE effectively cleanses input data and supervision targets via a tractable objective function produced by reparameterization mechanism and variational approximation. We extensively validate our method on four prevalent signed graph datasets, and the results show that RIDGE clearly improves the robustness of popular SGNN models under various levels of noise.