Iterative Graph Neural Network Enhancement via Frequent Subgraph Mining of Explanations
This addresses the problem of enhancing GNN accuracy for node classification tasks, though it appears incremental as it builds on existing explanation and subgraph mining methods.
The paper tackles improving Graph Neural Networks (GNNs) for node classification by using explanations to iteratively enhance predictive performance, showing that EEGL outperforms related approaches and extends node-distinguishing power beyond vanilla GNNs.
We formulate an XAI-based model improvement approach for Graph Neural Networks (GNNs) for node classification, called Explanation Enhanced Graph Learning (EEGL). The goal is to improve predictive performance of GNN using explanations. EEGL is an iterative self-improving algorithm, which starts with a learned "vanilla" GNN, and repeatedly uses frequent subgraph mining to find relevant patterns in explanation subgraphs. These patterns are then filtered further to obtain application-dependent features corresponding to the presence of certain subgraphs in the node neighborhoods. Giving an application-dependent algorithm for such a subgraph-based extension of the Weisfeiler-Leman (1-WL) algorithm has previously been posed as an open problem. We present experimental evidence, with synthetic and real-world data, which show that EEGL outperforms related approaches in predictive performance and that it has a node-distinguishing power beyond that of vanilla GNNs. We also analyze EEGL's training dynamics.