Toward Robust Signed Graph Learning through Joint Input-Target Denoising

2025-10-25

AI Summary

Existing signed graph neural networks (SGNNs) exhibit insufficient robustness to real-world noisy signed graphs and lack theoretical foundations. Method: This paper proposes RIDGE, the first framework to extend the graph information bottleneck principle to joint denoising of input graph structure and supervision signals. RIDGE formulates an optimizable joint purification objective via reparameterization and variational approximation, enabling coordinated cleaning of both graph topology and label space. Contribution/Results: RIDGE establishes the first information-theoretically grounded robust learning paradigm for signed graphs. Extensive experiments on four benchmark signed graph datasets demonstrate that RIDGE consistently enhances the performance of diverse SGNN architectures across varying noise levels, validating its effectiveness and strong generalization capability.

Technology Category

• Machine Learning: Graph-based Machine Learning
• Reasoning under Uncertainty: Graphical Models
• Search and Optimization: Learning to Search

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

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.

Problem

• Improving robustness of signed graph neural networks against noise
• Extending graph information bottleneck theory for target denoising
• Developing joint denoising framework for input and supervision targets

Innovation

• Joint denoising of graph inputs and targets
• Extended GIB theory for target space noise
• Tractable objective via reparameterization and approximation