Robust Learning on Noisy Graphs via Latent Space Constraints with External Knowledge

TL;DR

This paper introduces LSC-GNN, a novel method that uses external knowledge and latent space constraints to improve GNN robustness against noisy edges, enhancing performance and interpretability.

Contribution

The paper proposes LSC-GNN, a new approach that incorporates external clean links and latent space regularization to mitigate noise in graph neural networks.

Findings

LSC-GNN outperforms standard GNNs on benchmark datasets with noisy edges.

The method effectively reduces overfitting to spurious links.

Extension to heterogeneous graphs improves performance in biological networks.

Abstract

Graph Neural Networks (GNNs) often struggle with noisy edges. We propose Latent Space Constrained Graph Neural Networks (LSC-GNN) to incorporate external "clean" links and guide embeddings of a noisy target graph. We train two encoders--one on the full graph (target plus external edges) and another on a regularization graph excluding the target's potentially noisy links--then penalize discrepancies between their latent representations. This constraint steers the model away from overfitting spurious edges. Experiments on benchmark datasets show LSC-GNN outperforms standard and noise-resilient GNNs in graphs subjected to moderate noise. We extend LSC-GNN to heterogeneous graphs and validate it on a small protein-metabolite network, where metabolite-protein interactions reduce noise in protein co-occurrence data. Our results highlight LSC-GNN's potential to boost predictive performance and interpretability in settings with noisy relational structures.