Abstract
AbstractGraph Neural Networks (GNN) show good performance in relational data classification. However, their contribution to concept learning and the validation of their output from an application domain’s and user’s perspective have not been thoroughly studied. We argue that combining symbolic learning methods, such as Inductive Logic Programming (ILP), with statistical machine learning methods, especially GNNs, is an essential forward-looking step to perform powerful and validatable relational concept learning. In this contribution, we introduce a benchmark for the conceptual validation of GNN classification outputs. It consists of the symbolic representations of symmetric and non-symmetric figures that are taken from a well-known Kandinsky Pattern data set. We further provide a novel validation framework that can be used to generate comprehensible explanations with ILP on top of the relevance output of GNN explainers and human-expected relevance for concepts learned by GNNs. Our experiments conducted on our benchmark data set demonstrate that it is possible to extract symbolic concepts from the most relevant explanations that are representative of what a GNN has learned. Our findings open up a variety of avenues for future research on validatable explanations for GNNs.
Funder
Deutsche Forschungsgemeinschaft
Bundesministerium für Bildung und Forschung
Austrian Science Fund
Publisher
Springer Science and Business Media LLC
Reference70 articles.
1. Ravid Shwartz-Ziv and Naftali Tishby. Opening the Black Box of Deep Neural Networks via Information. Information Flow in Deep Neural Networks, page24, 2022
2. Zhou J, Cui G, Shengding H, Zhang Z, Yang C, Liu Z, Wang L, Li C, Sun M (2020) Graph neural networks: a review of methods and applications. AI Open 1:57–81
3. Keyulu X, Weihua H, Jure L, Stefanie J (2018) How powerful are graph neural networks? In: International conference on learning representations
4. Gabriel V (2002) Algorithms on Trees and Graphs, 112. Springer, New York
5. Horst B, Bruno TM (1993) Similarity measures for structured representations. In: European workshop on case-based reasoning, pp 106–118, Springer
Cited by
8 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献