aiqbench analysis
This research addresses the interpretability of Graph Neural Networks by deriving compact global logical rules from minimal abductive explanations, effectively filtering out node-specific redundancy to improve rule generality. The approach maintains high fidelity on benchmark datasets while offering a more efficient pathway for explaining predictions in Simple Graph Convolution networks compared to existing subgraph-based methods.
From Abductive Explanations to Global Logical Rules for Node Classification in SGCs
arXiv:2608.17103v1 Announce Type: new Abstract: 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.
Abstract: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.
Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Logic in Computer Science (cs.LO)
arXiv:2608.17103 [cs.LG]
(or arXiv:2608.17103v1 [cs.LG] for this version)
https://doi.org/10.48550/arXiv.2608.17103 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 251 words
Related coverage
The Entangled Dimensions of Decision Theory
LessWrong · Jul 30, 2026
HyDI: A hybrid Deep Learning-Inductive Logic Programming ensemble for multi-label classification
arXiv · Sep 30, 2026
P(Anyone Builds It & Everyone Dies) = 0.62?
LessWrong · Oct 16, 2026
Biological Superintelligence
LessWrong · Jul 30, 2026