BayesGrad: Explaining Predictions of Graph Convolutional Networks
This addresses the need for interpretability in graph-based machine learning for domains like chemistry, though it is incremental as it builds on existing Bayesian and dropout techniques.
The paper tackled the problem of explaining predictions from graph convolutional networks, particularly in chemical property prediction where small or imbalanced datasets cause uncertainty, by proposing BayesGrad to visualize important substructures, showing effectiveness in artificial and real experiments.
Recent advances in graph convolutional networks have significantly improved the performance of chemical predictions, raising a new research question: "how do we explain the predictions of graph convolutional networks?" A possible approach to answer this question is to visualize evidence substructures responsible for the predictions. For chemical property prediction tasks, the sample size of the training data is often small and/or a label imbalance problem occurs, where a few samples belong to a single class and the majority of samples belong to the other classes. This can lead to uncertainty related to the learned parameters of the machine learning model. To address this uncertainty, we propose BayesGrad, utilizing the Bayesian predictive distribution, to define the importance of each node in an input graph, which is computed efficiently using the dropout technique. We demonstrate that BayesGrad successfully visualizes the substructures responsible for the label prediction in the artificial experiment, even when the sample size is small. Furthermore, we use a real dataset to evaluate the effectiveness of the visualization. The basic idea of BayesGrad is not limited to graph-structured data and can be applied to other data types.