SEEN: Sharpening Explanations for Graph Neural Networks using Explanations from Neighborhoods
Explaining the foundations for predictions obtained from graph neural networks (GNNs) is critical for credible use of GNN models for real-world problems. Owing to the rapid growth of GNN applications, recent progress in explaining predictions from GNNs, such as sensitivity analysis, perturbation methods, and attribution methods, showed great opportunities and possibilities for explaining GNN predictions. In this study, we propose a method to improve the explanation quality of node classification tasks that can be applied in a post hoc manner through aggregation of auxiliary explanations from important neighboring nodes, named SEEN. Applying SEEN does not require modification of a graph and can be used with diverse explainability techniques due to its independent mechanism. Experiments on matching motif-participating nodes from a given graph show great improvement in explanation accuracy of up to 12.71% and demonstrate the correlation between the auxiliary explanations and the enhanced explanation accuracy through leveraging their contributions. SEEN provides a simple but effective method to enhance the explanation quality of GNN model outputs, and this method is applicable in combination with most explainability techniques.
Code (0)
등록된 구현이 없습니다.
Tasks
Node ClassificationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Locally Invariant Explanations: Towards Causal Explanations through Local Invariant Learning
Locally interpretable model agnostic explanations (LIME) method is one of the most popular methods used to explain black-box models at a per example level. Although many variants have been proposed, few provide a simple …
Out-of-Distribution GeneralizationLocally Invariant Explanations: Towards Stable and Unidirectional Explanations through Local Invariant Learning
Locally interpretable model agnostic explanations (LIME) method is one of the most popular methods used to explain black-box models at a per example level. Although many variants have been proposed, few provide a simple …
Out-of-Distribution GeneralizationELIXIR: Learning from User Feedback on Explanations to Improve Recommender Models
System-provided explanations for recommendations are an important component towards transparent and trustworthy AI. In state-of-the-art research, this is a one-way signal, though, to improve user acceptance. In this pape…
Iterative Graph Neural Network Enhancement via Frequent Subgraph Mining of Explanations
We formulate an XAI-based model improvement approach for Graph Neural Networks (GNNs) for node classification, called Explanation Enhanced Graph Learning (EEGL). The goal is to improve predictive performance of GNN using…
Graph LearningGraph Neural NetworkNode ClassificationThe Dangers of Post-hoc Interpretability: Unjustified Counterfactual Explanations
Post-hoc interpretability approaches have been proven to be powerful tools to generate explanations for the predictions made by a trained black-box model. However, they create the risk of having explanations that are a r…
counterfactual