Graph-based Integrated Gradients for Explaining Graph Neural Networks
This work addresses the explainability of graph neural networks for researchers and practitioners, but it is incremental as it adapts an existing method to a specific data type.
The authors tackled the problem of explaining graph neural networks by extending Integrated Gradients to handle discrete graph structures, demonstrating that their method accurately identifies crucial structural components on synthetic datasets and outperforms the original on real-world node classification tasks.
Integrated Gradients (IG) is a common explainability technique to address the black-box problem of neural networks. Integrated gradients assumes continuous data. Graphs are discrete structures making IG ill-suited to graphs. In this work, we introduce graph-based integrated gradients (GB-IG); an extension of IG to graphs. We demonstrate on four synthetic datasets that GB-IG accurately identifies crucial structural components of the graph used in classification tasks. We further demonstrate on three prevalent real-world graph datasets that GB-IG outperforms IG in highlighting important features for node classification tasks.