An Explainer refers to a component or tool that is specifically designed to provide explanations for the decisions made by an AI model. Explainers help bridge the gap between the complexity of AI algorithms and the need for human users to comprehend the rationale behind AI-generated outputs. Explainers can take various forms, such as textual or visual explanations, highlighting important features that influenced a decision, or presenting a step-by-step breakdown of the decision-making process. The purpose of an explainer is to make the AI system more interpretable and to enable users to trust and validate the system’s outputs, especially in sensitive domains like healthcare, finance, and criminal justice.


Parameterized Explainer for Graph Neural Network

Despite recent progress in Graph Neural Networks (GNNs), explaining predictions made by GNNs remains a challenging open problem. The leading method independently addresses the local explanations (i.e., important subgraph structure and node features) to interpret why a GNN model makes the prediction for a single instance, e.g. a node or a graph. As a result, the explanation generated is painstakingly customized for each instance. The unique explanation interpreting each instance independently is not sufficient to provide a global understanding of the learned GNN model, leading to the lack of generalizability and hindering it from being used in the inductive setting. Besides, as it is designed for explaining a single instance, it is challenging to explain a set of instances naturally (e.g., graphs of a given class). In this study, we address these key challenges and propose PGExplainer, a parameterized explainer for GNNs. PGExplainer adopts a deep neural network to parameterize the generation process of explanations, which enables PGExplainer a natural approach to explaining multiple instances collectively. Compared to the existing work, PGExplainer has better generalization ability and can be utilized in an inductive setting easily. Experiments on both synthetic and real-life datasets show highly competitive performance with up to 24.7% relative improvement in AUC on explaining graph classification over the leading baseline.