One-class graph autoencoder: A new end-to-end, low-dimensional, and interpretable approach for node classification

Autor(es)

Golo, Marcos Paulo Silva ; de Medeiros Jr, Jose Gilberto Barbosa de Medeiros ; Silva, Diego Furtado ; Marcacini, Ricardo Marcondes

• Tipo de documento: Artigo Científico
• Fonte: INFORMATION SCIENCES; v. 708, p. 17-pg., 2025-03-06.

Resumo

One-class learning (OCL) for graph neural networks (GNNs) comprises a set of techniques applied when real-world problems are modeled through graphs and have a single class of interest. These methods may employ a two-step strategy: first representing the graph and then classifying its nodes. End-to-end methods learn the node representations while classifying the nodes in OCL process. We highlight three main gaps in this literature: (i) non-customized representations for OCL; (ii) the lack of constraints on hypersphere learning; and (iii) the lack of interpretability. This paper presents One-cLass Graph Autoencoder (OLGA), a new OCL for GNN approach. OLGA is an end-to-end method that learns low-dimensional representations for nodes while encapsulating interest nodes through a proposed and new hypersphere loss function. Furthermore, OLGA combines this new hypersphere loss with the graph autoencoder reconstruction loss to improve model learning. The reconstruction loss is a constraint to the sole use of the hypersphere loss that can bias the model to encapsulate all nodes. Finally, our low-dimensional representation makes the OLGA interpretable since we can visualize the representation learning at each epoch. OLGA achieved state-of-the-art results and outperformed six other methods with statistical significance while maintaining the learning process interpretability with its low-dimensional representations. (AU)

• Processo FAPESP: 22/09091-8 - Criminalidade, insegurança e legitimidade: uma abordagem transdisciplinar
• Beneficiário: Luis Gustavo Nonato
• Modalidade de apoio: Auxílio à Pesquisa - Programa eScience e Data Science - Temático
• Processo FAPESP: 23/10100-4 - Desenvolvimento de Grandes Modelos de Língua para Aplicações no Domínio Jurídico
• Beneficiário: Ricardo Marcondes Marcacini
• Modalidade de apoio: Auxílio à Pesquisa - Pesquisa em Políticas Públicas
• Processo FAPESP: 23/02680-0 - Transferência de Aprendizado para Lidar com Heterogeneidade entre Dispositivos
• Beneficiário: José Gilberto Barbosa de Medeiros Júnior
• Modalidade de apoio: Bolsas no Brasil - Mestrado
• Processo FAPESP: 13/07375-0 - CeMEAI - Centro de Ciências Matemáticas Aplicadas à Indústria
• Beneficiário: Francisco Louzada Neto
• Modalidade de apoio: Auxílio à Pesquisa - Centros de Pesquisa, Inovação e Difusão - CEPIDs
• Processo FAPESP: 19/07665-4 - Centro de Inteligência Artificial
• Beneficiário: Fabio Gagliardi Cozman
• Modalidade de apoio: Auxílio à Pesquisa - Programa eScience e Data Science - Centros de Pesquisa em Engenharia