Explainability in Graph Neural Networks: A Taxonomic Survey

• Published in: IEEE transactions on pattern analysis and machine intelligence Vol. 45; no. 5; pp. 1 - 19
• Main Authors: Yuan, Hao, Yu, Haiyang, Gui, Shurui, Ji, Shuiwang
• Format: Journal Article
• Language: English
• Published: United States IEEE 01.05.2023; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Algorithms; Artificial Intelligence; Benchmarking; Biological system modeling; Data models; evaluation; explainability; Graph analysis; Graph neural networks; interpretability; Machine learning; Neural networks; Neural Networks, Computer; Predictive models; survey; Systematics; Task analysis; Taxonomy; Test stands
• ISSN: 0162-8828; 1939-3539; 2160-9292; 1939-3539
• DOI: 10.1109/TPAMI.2022.3204236

Deep learning methods are achieving ever-increasing performance on many artificial intelligence tasks. A major limitation of deep models is that they are not amenable to interpretability. This limitation can be circumvented by developing post hoc techniques to explain predictions, giving rise to the area of explainability. Recently, explainability of deep models on images and texts has achieved significant progress. In the area of graph data, graph neural networks (GNNs) and their explainability are experiencing rapid developments. However, there is neither a unified treatment of GNN explainability methods, nor a standard benchmark and testbed for evaluations. In this survey, we provide a unified and taxonomic view of current GNN explainability methods. Our unified and taxonomic treatments of this subject shed lights on the commonalities and differences of existing methods and set the stage for further methodological developments. To facilitate evaluations, we provide a testbed for GNN explainability, including datasets, common algorithms and evaluation metrics. Furthermore, we conduct comprehensive experiments to compare and analyze the performance of many techniques. Altogether, this work provides a unified methodological treatment of GNN explainability and a standardized testbed for evaluations.