Edge-Level Explanations for Graph Neural Networks by Extending Explainability Methods for Convolutional Neural Networks
Graph Neural Networks (GNNs) are deep learning models that take graph data as inputs, and they are applied to various tasks such as traffic prediction and molecular property prediction. However, owing to the complexity of the GNNs, it has been difficult to analyze which parts of inputs affect the GNN model's outputs. In this study, we extend explainability methods for Convolutional Neural Networks (CNNs), such as Local Interpretable Model-Agnostic Explanations (LIME), Gradient-Based Saliency Maps, and Gradient-Weighted Class Activation Mapping (Grad-CAM) to GNNs, and predict which edges in the input graphs are important for GNN decisions. The experimental results indicate that the LIME-based approach is the most efficient explainability method for multiple tasks in the real-world situation, outperforming even the state-of-the-art method in GNN explainability.
Code (0)
등록된 구현이 없습니다.
Tasks
Molecular Property PredictionProperty PredictionTraffic PredictionSimilar Papers 제목 키워드 기반
Unifying Post-hoc Explanations of Knowledge Graph Completions
Knowledge Graphs organize information as entity-relation-entity triples, enabling machine learning models to predict plausible missing triples in a task known as Knowledge Graph Completion (KGC). Post-hoc explainability …
Knowledge Graph CompletionKnowledge GraphsA Completion-Aware Framework for Impactful Counterfactual Explainability in Graph Neural Networks
In this study, we propose a novel pipeline for generic, model-agnostic, local-level counterfactual explainability in graph neural networks (GNNs). Although counterfactual explainers capable of both adding and removing ed…
Explanation GenerationGraph ClassificationLink PredictionTowards Faithful Class-level Self-explainability in Graph Neural Networks by Subgraph Dependencies
Enhancing the interpretability of graph neural networks (GNNs) is crucial to ensure their safe and fair deployment. Recent work has introduced self-explainable GNNs that generate explanations as part of training, improvi…
Graph ClassificationD4Explainer: In-Distribution GNN Explanations via Discrete Denoising Diffusion
The widespread deployment of Graph Neural Networks (GNNs) sparks significant interest in their explainability, which plays a vital role in model auditing and ensuring trustworthy graph learning. The objective of GNN expl…
counterfactualDenoisingGraph LearningD4Explainer: In-distribution Explanations of Graph Neural Network via Discrete Denoising Diffusion
The widespread deployment of Graph Neural Networks (GNNs) sparks significant interest in their explainability, which plays a vital role in model auditing and ensuring trustworthy graph learning. The objective of GNN expl…