SyncAI.news, a Varaisys broadcasting
Learning the Graph and the Embedding Together: Classifier-Independent Rewiring for Heterophilic Node Classification
HK

Harshit Kumar, Sujan Chakraborty, Priyanka Saha, Pritam Kar, Saptarshi Bej

· 1 min read

ResearcharXiv cs.LG

Learning the Graph and the Embedding Together: Classifier-Independent Rewiring for Heterophilic Node Classification

arXiv:2609.32613v1 Announce Type: new Abstract: Graph neural networks lose much of their advantage on heterophilic graphs, where connected nodes often carry different labels. Graph rewiring is a popular remedy, but rewiring methods are usually evaluated with a single classifier, which makes it hard to tell whether the gains come from the new topology or from that particular pairing. We propose an affinity-guided rewiring method that estimates the graph and the node representation together. It alternates, in the spirit of expectation maximisation, between training a lightweight graph neural network on the current graph and re-weighting candidate edges under a modularity objective with a pseudo-label homophily term. Candidate edges come from a compact pool scored by a contrastively learned node similarity and a neighbourhood-distribution affinity. The method returns two classifier-independent outputs: a rewired graph and a node embedding learned on it. Across six heterophilic benchmarks and five downstream classifiers, it improves accuracy over the original graph with normalised features in 23 of 30 classifier-dataset combinations, with a mean gain of 5.8 points, and reduces the accuracy spread between classifiers about fourfold. A controlled ablation shows that the two outputs are each useful and play complementary roles: the embedding contributes most of the accuracy gain, while the rewired graph makes different classifiers agree. A fully unsupervised variant, which uses no labels during rewiring, retains most of the improvement. The rewired graphs are also more homophilic and improve label propagation and community detection.

Original source

This story was published by arXiv cs.LG and written by Harshit Kumar, Sujan Chakraborty, Priyanka Saha, Pritam Kar, Saptarshi Bej. SyncAI.news shows a preview; the complete article is on the publisher's site.

Read the full story on arxiv.org

Similar News