Higher-Order Explanations of Graph Neural Networks via Relevant Walks
This addresses the need for explainable AI in graph-structured data, providing a novel approach to interpret GNNs, though it is incremental as it builds on existing techniques like LRP.
The paper tackles the problem of explaining Graph Neural Networks (GNNs), which are often black-box models, by proposing a method that uses higher-order expansions to identify groups of edges that jointly contribute to predictions, enabling extraction of relevant walks for insights in sentiment analysis, quantum chemistry, and image classification.
Graph Neural Networks (GNNs) are a popular approach for predicting graph structured data. As GNNs tightly entangle the input graph into the neural network structure, common explainable AI approaches are not applicable. To a large extent, GNNs have remained black-boxes for the user so far. In this paper, we show that GNNs can in fact be naturally explained using higher-order expansions, i.e. by identifying groups of edges that jointly contribute to the prediction. Practically, we find that such explanations can be extracted using a nested attribution scheme, where existing techniques such as layer-wise relevance propagation (LRP) can be applied at each step. The output is a collection of walks into the input graph that are relevant for the prediction. Our novel explanation method, which we denote by GNN-LRP, is applicable to a broad range of graph neural networks and lets us extract practically relevant insights on sentiment analysis of text data, structure-property relationships in quantum chemistry, and image classification.