| Texto completo | |
| Autor(es): |
dos Santos, Nicolas R.
;
Minatel, Diego
;
Valejo, Alan D. B.
;
Lopes, Alneu A.
Número total de Autores: 4
|
| Tipo de documento: | Artigo Científico |
| Fonte: | 40TH ANNUAL ACM SYMPOSIUM ON APPLIED COMPUTING; v. N/A, p. 3-pg., 2025-01-01. |
| Resumo | |
Graph Neural Networks (GNNs) have shown remarkable success in text classification through diverse graph types for representing a corpus and strategies to enrich their structure. In this context, bipartite graphs are particularly effective due to their ability to represent dyadic interactions naturally. However, when the focus is on analyzing a single entity type, one-mode projection stands out as a prominent technique. Specifically, it transforms bipartite graphs into unipartite ones consisting of a single node type, linking them based on shared neighbors from the other type. While one-mode projection has been utilized in machine learning, its potential for GNN-based text classification remains unexplored. To address this gap, we propose a novel method called One-mode Projection of Bipartite Graphs for Text Classification (OPTIC). Concretely, OPTIC projects the document partition of a document-word bipartite graph and applies a GNN to the unipartite graph for text classification. Experiments on eight datasets show that OPTIC achieves on-par accuracy on all datasets compared to the baselines. Code and supplementary material are available at https://github.com/nicolasrsantos/optic. (AU) | |
| Processo FAPESP: | 22/03090-0 - Análise de grandes volumes de dados políticos e redes complexas: mineração, modelagens e aplicações em Ciência Política Computacional |
| Beneficiário: | Sylvia Iasulaitis |
| Modalidade de apoio: | Auxílio à Pesquisa - Projeto Inicial |
| Processo FAPESP: | 20/09835-1 - IARA - Inteligência Artificial Recriando Ambientes |
| Beneficiário: | André Carlos Ponce de Leon Ferreira de Carvalho |
| Modalidade de apoio: | Auxílio à Pesquisa - Programa Centros de Pesquisa Aplicada |
| 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: | 21/06210-3 - Serviços cientes dos espaços urbanos via federated learning em sistemas de transporte inteligente |
| Beneficiário: | Geraldo Pereira Rocha Filho |
| Modalidade de apoio: | Auxílio à Pesquisa - Regular |