Timezone: »

Parameterized Explainer for Graph Neural Network
Dongsheng Luo · Wei Cheng · Dongkuan Xu · Wenchao Yu · Bo Zong · Haifeng Chen · Xiang Zhang

Thu Dec 10 09:00 AM -- 11:00 AM (PST) @ Poster Session 5 #1722

Despite recent progress in Graph Neural Networks (GNNs), explaining predictions made by GNNs remains a challenging open problem. The leading method mainly 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 multi-instance explanations. Compared to the existing work, PGExplainer has a better generalization power 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.

Author Information

Dongsheng Luo (The Pennsylvania State University)
Wei Cheng (NEC Labs America)
Dongkuan Xu (The Pennsylvania State University)
Wenchao Yu (UCLA)
Bo Zong (NEC Labs)
Haifeng Chen (NEC Labs America)
Xiang Zhang (The Pennsylvania State University)

More from the Same Authors