Graph neural networks (GNNs) are popular machine learning models for graphs
with many applications across scientific domains. However, GNNs are considered
black box models, and it is challenging to understand how the model makes
predictions. Game theory-based Shapley value approaches are popular explanation
methods in other domains but are not well-studied for graphs. Some studies have
proposed Shapley value-based GNN explanations, yet they have several
limitations: they consider limited samples to approximate Shapley values; some
mainly focus on small and large coalition sizes, and they are an order of
magnitude slower than other explanation methods, making them inapplicable to
even moderate-size graphs. In this work, we propose GNNShap, which provides
explanations for edges since they provide more natural explanations for graphs
and more fine-grained explanations. We overcome the limitations by sampling
from all coalition sizes, parallelizing the sampling on GPUs, and speeding up
model predictions by batching. GNNShap gives better fidelity scores and faster
explanations than baselines on real-world datasets.

本研究提出了 GNNShap 方法，通过并行化抽样、批处理加速模型预测，为边提供更自然和细粒度的图解释，克服了样本数有限、速度慢等限制，并在真实数据集上取得了较好的可信度分数和更快的解释。