In this paper, we investigate the degree of explainability of graph neural networks (GNNs). Existing explainers work by finding global/local subgraphs to explain a prediction, but they are applied after a GNN has already been trained. Here, we propose a meta-learning framework for improving the level of explainability of a GNN directly at training time, by steering the optimization procedure towards what we call `interpretable minima'. Our framework (called MATE, MetA-Train to Explain) jointly trains a model to solve the original task, e.g., node classification, and to provide easily processable outputs for downstream algorithms that explain the model's decisions in a human-friendly way. In particular, we meta-train the model's parameters to quickly minimize the error of an instance-level GNNExplainer trained on-the-fly on randomly sampled nodes. The final internal representation relies upon a set of features that can be `better' understood by an explanation algorithm, e.g., another instance of GNNExplainer. Our model-agnostic approach can improve the explanations produced for different GNN architectures and use any instance-based explainer to drive this process. Experiments on synthetic and real-world datasets for node and graph classification show that we can produce models that are consistently easier to explain by different algorithms. Furthermore, this increase in explainability comes at no cost for the accuracy of the model.
翻译:在本文中,我们调查了图形神经网络(GNNs)的解释性程度。现有的解释者通过寻找全球/地方子子集来解释预测而工作。现有的解释者通过寻找全球/地方子子集来解释预测,但在GNN已经受过培训之后应用。在这里,我们提议了一个元学习框架,以提高GNNN直接在培训时的解释性水平,将优化程序引导到我们所谓的“可解释的微型网点”上。我们的框架(称为MATE,MetA-Train to Exploration)联合培训一个模型,以解决原始任务,例如,诺德分类,并为下游算法提供易于处理的产出,以人类友好的方式解释模型的决定。特别是,我们用模型参数来迅速减少在培训时直接培训的像样级GNNNExplainlainer的错误。我们的最后内部代表取决于一套能够通过解释算法“更简单”的模型,例如,另一个基于GNNEXDLA的示例,我们这个模型-Annexlistrual 方法可以改进用于不同的GNNSAlistrical Procumental Proturations 和GNS-deal-deal Produstrations produstruts produstruts