Graph Convolutional Networks and Particle Competition and Cooperation for Semi-Supervised Learning

• Main Author: Leticio, Gustavo Rosseto [UNESP]
• Publication Date: 2025
• Other Authors: Dos Santos, Matheus Henrique Jacob [UNESP], Valem, Lucas Pascotti [UNESP], Kawai, Vinicius Atsushi Sato [UNESP], Breve, Fabricio Aparecido [UNESP], Pedronette, Daniel Carlos Guimarães [UNESP]
• Format: Conference object
• Language: eng
• Source: Repositório Institucional da UNESP
• Download full: http://dx.doi.org/10.5220/0013267000003912; https://hdl.handle.net/11449/307030
• topic: Graph Convolutional Networks; Particle Competition and Cooperation; Semi-Supervised Learning

Given the substantial challenges associated with obtaining labeled data, including high costs, time consumption, and the frequent need for expert involvement, semi-supervised learning has garnered increased attention. In these scenarios, Graph Convolutional Networks (GCNs) offer an attractive and promising solution, as they can effectively leverage labeled and unlabeled data for classification. Through their ability to capture complex relationships within data, GCNs provide a powerful framework for tasks that rely on limited labeled information. There are also other promising approaches that exploit the graph structure for more effective learning, such as the Particle Competition and Cooperation (PCC), an algorithm that models label propagation through particles that compete and cooperate on a graph constructed from the data, exploiting similarity relationships between instances. In this work, we propose a novel approach that combines PCC, GCN, and dimensionality reduction approaches for improved classification performance. The experimental results showed that our method provided gains in most cases.