Joint Graph Rewiring and Feature Denoising via Spectral Resonance
Keywords: GNNs, Rewiring, Denoising, Spectral Resonance, cSBM
TL;DR: We introduce joint denoising and rewiring (JDR)—an algorithm to jointly rewire the graph and denoise the features, which improves the performance of downstream node classification GNNs.
Abstract: In graph learning the graph and the node features both contain noisy information about the node labels. In this paper we propose joint denoising and rewiring (JDR)—an algorithm to jointly rewire the graph and denoise the features, which improves the performance of downstream node classification graph neural nets (GNNs). JDR improves the alignment between the leading eigenspaces of graph and feature matrices. To approximately solve the associated non-convex optimization problem we propose a heuristic that efficiently handles real-world graph datasets with multiple classes and different levels of homophily or heterophily. We theoretically justify JDR in a stylized setting and verify the effectiveness of our approach through extensive experiments on synthetic and real-world graph datasets. The results show that JDR consistently outperforms existing rewiring methods on node classification using GNNs as downstream models.
Primary Area: learning on graphs and other geometries & topologies
Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.
Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2025/AuthorGuide.
Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.
No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.
Submission Number: 11879
Loading