论文标题
对比图神经网络解释
Contrastive Graph Neural Network Explanation
论文作者
论文摘要
图神经网络在结构化数据的问题上取得了显着的结果，但作为黑框预测变量。转移现有的解释技术（例如遮挡）失败了，因为即使删除单个节点或边缘也会导致图表的急剧变化。最终的图可能与所有训练示例不同，从而导致模型混乱和错误的解释。因此，我们认为可解释性必须使用与训练数据基础分布的图表。我们在此范围内构造了这种属性分布的说明（DCE），并提出了一种新颖的对比GNN解释（COGE）技术。一项实验研究支持副毛的功效。
Graph Neural Networks achieve remarkable results on problems with structured data but come as black-box predictors. Transferring existing explanation techniques, such as occlusion, fails as even removing a single node or edge can lead to drastic changes in the graph. The resulting graphs can differ from all training examples, causing model confusion and wrong explanations. Thus, we argue that explicability must use graphs compliant with the distribution underlying the training data. We coin this property Distribution Compliant Explanation (DCE) and present a novel Contrastive GNN Explanation (CoGE) technique following this paradigm. An experimental study supports the efficacy of CoGE.
