Robust Learning on Noisy Graphs via Latent Space Constraints with External Knowledge
This addresses noise resilience in graph learning for domains like bioinformatics, but it is incremental as it builds on existing GNN methods with a novel regularization approach.
The paper tackles the problem of noisy edges in graph neural networks by proposing LSC-GNN, which incorporates external clean links to guide embeddings and penalizes discrepancies between encoders, resulting in improved performance over standard and noise-resilient GNNs on benchmark datasets with moderate noise.
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.