English static mirror for SEO/GEO · AI-assisted translation · Read Chinese original

Particle Competition and Cooperation for Robust Graph Convolutional Networks Against Label Noise (PCC+GCN)

Forum topic · 小凯 · 2026-09-22

Summary

Graph Convolutional Networks (GCNs) are highly sensitive to label noise because corrupted supervision propagates through the graph and degrades learned node representations. This work proposes PCC+GCN, a hybrid framework by Fabricio Breve (arXiv:2609.22053) that applies Particle Competition and Cooperation (PCC) as a graph-based label-refinement stage before GCN training. PCC identifies suspicious labeled nodes through particle domination dynamics and decides whether their labels should be preserved, removed, or reassigned. Optionally, the PCC graph can be augmented with feature-based k-nearest-neighbor edges while the GCN trains on the original graph structure and features. Evaluated on ten graph datasets from the NoisyGL benchmark under Uniform, Pair, Random, and instance-dependent label noise, PCC+GCN achieved the highest overall average accuracy and best average rank under conventional noise, improving baseline GCN by 1.67 percentage points on average. Under instance-dependent noise it remained competitive with the most robust methods while running significantly faster, being the fastest robust method on eight of ten datasets. The results demonstrate PCC-based label refinement as an effective and computationally efficient preprocessing strategy for improving GCN robustness under noisy supervision.

Paper Overview

Field: Machine Learning Author: Fabricio Breve Published: 2026-09-18 arXiv: 2609.22053

Abstract

Graph Convolutional Networks (GCNs) are highly sensitive to label noise, since corrupted supervision can propagate through the graph and degrade learned node representations. This work proposes PCC+GCN, a hybrid framework that uses Particle Competition and Cooperation (PCC) as a graph-based label-refinement stage before GCN training.

PCC identifies suspicious labeled nodes through particle domination dynamics and determines whether their labels should be preserved, removed, or reassigned before GCN training. The framework also allows the graph used by PCC to be augmented with feature-based \(k\)-nearest-neighbor edges, while the GCN itself is trained on the original graph structure and node features.

Key Results

  • Benchmark: Evaluated on ten graph datasets from the NoisyGL benchmark, covering conventional Uniform, Pair, and Random label noise, as well as instance-dependent label noise. A detailed hyperparameter analysis was conducted on Cora, CiteSeer, and PubMed.
  • Conventional noise: PCC+GCN achieved the highest overall average accuracy and the best average rank among all evaluated methods, outperforming baseline GCN by 1.67 percentage points on average in the clean setting and across all noise scenarios.
  • Instance-dependent noise: PCC+GCN remained competitive with the most robust methods while requiring significantly less execution time — it was the fastest robust method on eight of the ten datasets.
  • Conclusion: PCC-based label refinement is an effective and computationally efficient preprocessing strategy for improving GCN robustness under noisy supervision.

Link

Full paper: https://arxiv.org/abs/2609.22053

Tags

#graph-convolutional-networks#label-noise#particle-competition#semi-supervised-learning#graph-machine-learning#robustness#arxiv

This page is an English static mirror generated for search and AI citation. It may be a full translation or structured summary of the Chinese original. Canonical interactive discussion lives on the Chinese page: https://zhichai.net/topic/178635071