Explainability in Graph Neural Networks: A Taxonomic Survey

By Hao Yuan, Haiyang Yu, Shurui Gui, Shuiwang Ji. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2020

842 citations recorded by the source corpus.

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.

Subfields: Artificial Intelligence

View Paper: https://www.semanticscholar.org/paper/6ae2967bb0a5e57cc545176120a4845576e068a3

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

Citations in the corpus

Higher-Order Explanations of Graph Neural Networks via Relevant Walks (2020, background): “We also found that the activation and pruning tasks are very similar to the fidelity and sparsity tasks presented in [24] and [35].”
Self-Supervised Learning of Graph Neural Networks: A Unified Review (2021, methodology): “A survey work [127] provides a thorough introduction to existing explanation methods for GNNs.”
On Explainability of Graph Neural Networks via Subgraph Explorations (2021, methodology): “The XGNN can obtain graph patterns to explain GNNs but its explanations are not input-dependent and less precise.”
Explainable AI (XAI): A Systematic Meta-Survey of Current Challenges and Future Opportunities (2021, methodology): “For example, existing explanation approaches for image or text data need to be adjusted to be used with graph data (without any transformation) [57].”
Graph Neural Networks in Recommender Systems: A Survey (2020, methodology): “With the proliferation of GNN, recent efforts have investigated GNN explainability methods [193].”
A Survey of Knowledge Graph Reasoning on Graph Types: Static, Dynamic, and Multi-Modal (2022, background): “However, most existing artiﬁcial intelligence (AI) models only imitate the learning procedure from experiences while ignoring the former [1], [2], thus making them less explainable and worse performances.”