Geometric Imbalance in Semi-Supervised Node Classification

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Yan, Liang, Zhang, Shengzhong, Li, Bisheng, Yang, Menglin, Yang, Chen, Zhou, Min, Ding, Weiyang, Xie, Yutong, Huang, Zengfeng
Natura: Preprint
Pubblicazione: 2023
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866908902958825472
author Yan, Liang
Zhang, Shengzhong
Li, Bisheng
Yang, Menglin
Yang, Chen
Zhou, Min
Ding, Weiyang
Xie, Yutong
Huang, Zengfeng
author_facet Yan, Liang
Zhang, Shengzhong
Li, Bisheng
Yang, Menglin
Yang, Chen
Zhou, Min
Ding, Weiyang
Xie, Yutong
Huang, Zengfeng
contents Class imbalance in graph data presents a significant challenge for effective node classification, particularly in semi-supervised scenarios. In this work, we formally introduce the concept of geometric imbalance, which captures how message passing on class-imbalanced graphs leads to geometric ambiguity among minority-class nodes in the riemannian manifold embedding space. We provide a rigorous theoretical analysis of geometric imbalance on the riemannian manifold and propose a unified framework that explicitly mitigates it through pseudo-label alignment, node reordering, and ambiguity filtering. Extensive experiments on diverse benchmarks show that our approach consistently outperforms existing methods, especially under severe class imbalance. Our findings offer new theoretical insights and practical tools for robust semi-supervised node classification.
format Preprint
id arxiv_https___arxiv_org_abs_2303_10371
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Geometric Imbalance in Semi-Supervised Node Classification
Yan, Liang
Zhang, Shengzhong
Li, Bisheng
Yang, Menglin
Yang, Chen
Zhou, Min
Ding, Weiyang
Xie, Yutong
Huang, Zengfeng
Machine Learning
Class imbalance in graph data presents a significant challenge for effective node classification, particularly in semi-supervised scenarios. In this work, we formally introduce the concept of geometric imbalance, which captures how message passing on class-imbalanced graphs leads to geometric ambiguity among minority-class nodes in the riemannian manifold embedding space. We provide a rigorous theoretical analysis of geometric imbalance on the riemannian manifold and propose a unified framework that explicitly mitigates it through pseudo-label alignment, node reordering, and ambiguity filtering. Extensive experiments on diverse benchmarks show that our approach consistently outperforms existing methods, especially under severe class imbalance. Our findings offer new theoretical insights and practical tools for robust semi-supervised node classification.
title Geometric Imbalance in Semi-Supervised Node Classification
topic Machine Learning
url https://arxiv.org/abs/2303.10371