Skip to yearly menu bar Skip to main content


Poster

Joint Graph Rewiring and Feature Denoising via Spectral Resonance

Jonas Linkerhägner · Cheng Shi · Ivan Dokmanić

Hall 3 + Hall 2B #201
[ ] [ Project Page ]
Fri 25 Apr midnight PDT — 2:30 a.m. PDT
 
Oral presentation: Oral Session 2E
Thu 24 Apr 12:30 a.m. PDT — 2 a.m. PDT

Abstract:

When learning from graph data, the graph and the node features both give noisy information about the node labels. In this paper we propose an algorithm to jointly denoise the features and rewire the graph (JDR), which improves the performance of downstream node classification graph neural nets (GNNs). JDR works by aligning the leading spectral spaces of graph and feature matrices. It approximately solves the associated non-convex optimization problem in a way that handles graphs with multiple classes and different levels of homophily or heterophily. We theoretically justify JDR in a stylized setting and show that it consistently outperforms existing rewiring methods on a wide range of synthetic and real-world node classification tasks.

Live content is unavailable. Log in and register to view live content