{"ID":2875421,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2509.10510","arxiv_id":"2509.10510","title":"FireGNN: Neuro-Symbolic Graph Neural Networks with Trainable Fuzzy Rules for Interpretable Medical Image Classification","abstract":"Medical image classification requires not only high predictive performance but also interpretability to ensure clinical trust and adoption. Graph Neural Networks (GNNs) offer a powerful framework for modeling relational structures within datasets; however, standard GNNs often operate as black boxes, limiting transparency and usability, particularly in clinical settings. In this work, we present an interpretable graph-based learning framework named FireGNN that integrates trainable fuzzy rules into GNNs for medical image classification. These rules embed topological descriptors - node degree, clustering coefficient, and label agreement - using learnable thresholds and sharpness parameters to enable intrinsic symbolic reasoning. Additionally, we explore auxiliary self-supervised tasks (e.g., homophily prediction, similarity entropy) as a benchmark to evaluate the contribution of topological learning. Our fuzzy-rule-enhanced model achieves strong performance across five MedMNIST benchmarks and the synthetic dataset MorphoMNIST, while also generating interpretable rule-based explanations. To our knowledge, this is the first integration of trainable fuzzy rules within a GNN. Source Code: https://github.com/basiralab/FireGNN","short_abstract":"Medical image classification requires not only high predictive performance but also interpretability to ensure clinical trust and adoption. Graph Neural Networks (GNNs) offer a powerful framework for modeling relational structures within datasets; however, standard GNNs often operate as black boxes, limiting transparen...","url_abs":"https://arxiv.org/abs/2509.10510","url_pdf":"https://arxiv.org/pdf/2509.10510v2","authors":"[\"Prajit Sengupta\",\"Islem Rekik\"]","published":"2025-09-02T12:57:54Z","proceeding":"eess.IV","tasks":"[\"eess.IV\",\"cs.AI\",\"cs.CV\",\"cs.LG\"]","methods":"[\"Graph Neural Network\"]","has_code":false,"code_links":[{"ID":610209,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2875421,"paper_url":"https://arxiv.org/abs/2509.10510","paper_title":"FireGNN: Neuro-Symbolic Graph Neural Networks with Trainable Fuzzy Rules for Interpretable Medical Image Classification","repo_url":"https://github.com/basiralab/FireGNN","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}