Globally Interpretable Graph Learning via Distribution Matching

arXiv:2306.10447v2 Announce Type: replace
Abstract: Graph neural networks (GNNs) have emerged as a powerful model to capture critical graph patterns. Instead of treating them as black boxes in an end-to-end fashion, attempts are arising to explain the model behavior. Existing works mainly focus on local interpretation to reveal the discriminative pattern for each individual instance, which however cannot directly reflect the high-level model behavior across instances. To gain global insights, we aim to answer an important question that is not …

abstract arxiv behavior black boxes cs.lg distribution fashion focus gnns graph graph learning graph neural networks interpretation model behavior networks neural networks patterns them type via