{"ID":2882234,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2508.10461","arxiv_id":"2508.10461","title":"X-Node: Self-Explanation is All We Need","abstract":"Graph neural networks (GNNs) have achieved state-of-the-art results in computer vision and medical image classification tasks by capturing structural dependencies across data instances. However, their decision-making remains largely opaque, limiting their trustworthiness in high-stakes clinical applications where interpretability is essential. Existing explainability techniques for GNNs are typically post-hoc and global, offering limited insight into individual node decisions or local reasoning. We introduce X-Node, a self-explaining GNN framework in which each node generates its own explanation as part of the prediction process. For every node, we construct a structured context vector encoding interpretable cues such as degree, centrality, clustering, feature saliency, and label agreement within its local topology. A lightweight Reasoner module maps this context into a compact explanation vector, which serves three purposes: (1) reconstructing the node's latent embedding via a decoder to enforce faithfulness, (2) generating a natural language explanation using a pre-trained LLM (e.g., Grok or Gemini), and (3) guiding the GNN itself via a \"text-injection\" mechanism that feeds explanations back into the message-passing pipeline. We evaluate X-Node on two graph datasets derived from MedMNIST and MorphoMNIST, integrating it with GCN, GAT, and GIN backbones. Our results show that X-Node maintains competitive classification accuracy while producing faithful, per-node explanations. Repository: https://github.com/basiralab/X-Node.","short_abstract":"Graph neural networks (GNNs) have achieved state-of-the-art results in computer vision and medical image classification tasks by capturing structural dependencies across data instances. However, their decision-making remains largely opaque, limiting their trustworthiness in high-stakes clinical applications where inter...","url_abs":"https://arxiv.org/abs/2508.10461","url_pdf":"https://arxiv.org/pdf/2508.10461v1","authors":"[\"Prajit Sengupta\",\"Islem Rekik\"]","published":"2025-08-14T09:00:45Z","proceeding":"cs.LG","tasks":"[\"cs.LG\",\"cs.AI\"]","methods":"[\"Graph Neural Network\",\"Large Language Model\"]","has_code":false,"code_links":[{"ID":610871,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2882234,"paper_url":"https://arxiv.org/abs/2508.10461","paper_title":"X-Node: Self-Explanation is All We Need","repo_url":"https://github.com/basiralab/X-Node","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}