Pluska, A., Welke, P., Gärtner, T., & Malhotra, S. (2024). Logical Distillation of Graph Neural Networks. In P. Marquis, M. Ortiz, & M. Pagnucco (Eds.), Proceedings of the 21st International Conference on Principles of Knowledge Representation and Reasoning (pp. 920–930). IJCAI Organization. https://doi.org/10.24963/kr.2024/86
We present a logic based interpretable model for learning on graphs and an algorithm to distill this model from a Graph Neural Network (GNN). Recent results have shown connections between the expressivity of GNNs and the two-variable fragment of first-order logic with counting quantifiers (C2). We introduce a decision-tree based model which leverages an extension of C2 to distill interpretable logical classifiers from GNNs. We test our approach on multiple GNN architectures. The distilled models are interpretable, succinct, and attain similar accuracy to the underlying GNN. Furthermore, when the ground truth is expressible in C2, our approach outperforms the GNN.
en
Project title:
Structured Data Learning with Generalized Similarities: ICT22-059 (WWTF Wiener Wissenschafts-, Forschu und Technologiefonds) NanoX: I 6728 (FWF - Österr. Wissenschaftsfonds) Training Alliance for Computational Systems chemistry: Proposal number: 101072930 (European Commission)
-
Research Areas:
Logic and Computation: 50% Information Systems Engineering: 50%
