Saved in:
Bibliographic Details
Main Authors: Gu, Chunhui, Nasr, Mohammad Sadegh, Long, James P., Do, Kim-Anh, Irajizad, Ehsan
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2507.05540
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909678929182720
author Gu, Chunhui
Nasr, Mohammad Sadegh
Long, James P.
Do, Kim-Anh
Irajizad, Ehsan
author_facet Gu, Chunhui
Nasr, Mohammad Sadegh
Long, James P.
Do, Kim-Anh
Irajizad, Ehsan
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2507_05540
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Robust Learning on Noisy Graphs via Latent Space Constraints with External Knowledge
Gu, Chunhui
Nasr, Mohammad Sadegh
Long, James P.
Do, Kim-Anh
Irajizad, Ehsan
Machine Learning
Artificial Intelligence
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.
title Robust Learning on Noisy Graphs via Latent Space Constraints with External Knowledge
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2507.05540