Joint Graph Rewiring and Feature Denoising via Spectral Resonance
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866912335789031424 |
|---|---|
| author | Linkerhägner, Jonas Shi, Cheng Dokmanić, Ivan |
| author_facet | Linkerhägner, Jonas Shi, Cheng Dokmanić, Ivan |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2408_07191 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Joint Graph Rewiring and Feature Denoising via Spectral Resonance Linkerhägner, Jonas Shi, Cheng Dokmanić, Ivan Machine Learning Social and Information Networks 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. |
| title | Joint Graph Rewiring and Feature Denoising via Spectral Resonance |
| topic | Machine Learning Social and Information Networks |
| url | https://arxiv.org/abs/2408.07191 |