Metraipolis › archive › dc_3154512cf28c
From Abductive Explanations to Global Logical Rules for Node Classification in SGCs — arXiv:2608.17103
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.17103
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-18T14:29:10.374Z
- SHA-256 of the archived text
1029bfa4bf2d454e1919f2376337df675a89d1711a19eb48e08d09cc1b6e8fd6- Stable URL of this page
https://metraipolis.com/documento/dc_3154512cf28c
How to cite
From Abductive Explanations to Global Logical Rules for Node Classification in SGCs — arXiv:2608.17103 — arXiv (en), https://arxiv.org/abs/2608.17103 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_3154512cf28c (Metraipolis archive dc_3154512cf28c, sha256 1029bfa4bf2d454e1919f2376337df675a89d1711a19eb48e08d09cc1b6e8fd6)
BibTeX
@misc{dc3154512cf28c,
title = {From Abductive Explanations to Global Logical Rules for Node Classification in SGCs — arXiv:2608.17103},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.17103},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_3154512cf28c; sha256 1029bfa4bf2d454e1919f2376337df675a89d1711a19eb48e08d09cc1b6e8fd6},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.17103. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Graph Neural Networks (GNNs) have achieved remarkable performance in node classification tasks, motivating growing interest in methods capable of explaining their predictions. Recent logic-based approaches, such as LogicXGNN, derive global logical rules for Graph Neural Networks (GNNs) from collections of explanatory subgraphs. While informative, these subgraphs may contain redundant structural information that is specific to individual nodes, potentially limiting the generality of the extracted rules. In this work, we propose a logic-based framework for node classification in Simple Graph Convolution (SGC) networks that uses minimal abductive explanations as an intermediate representation for rule extraction. For each node, we compute a minimal set of node-feature pairs sufficient to preserve the predicted class. These explanations are then used to train decision trees from which global logical rules are extracted. Experiments on benchmark datasets show that the proposed framework produces compact global rules while maintaining high fidelity to the original SGC model. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-19 in cs.AI). Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI); Logic in Computer Science (cs.LO). Pagina del lavoro: https://arxiv.org/abs/2608.17103 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-18T14:27:54.372Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-19?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).