Exploring Explainability Methods for Graph Neural Networks
With the growing use of deep learning methods, particularly graph neural networks, which encode intricate interconnectedness information, for a variety of real tasks, there is a necessity for explainability in such settings. In this paper, we demonstrate the applicability of popular explainability approaches on Graph Attention Networks (GAT) for a graph-based super-pixel image classification task. We assess the qualitative and quantitative performance of these techniques on three different datasets and describe our findings. The results shed a fresh light on the notion of explainability in GNNs, particularly GATs.
Code (0)
등록된 구현이 없습니다.
Tasks
Graph Attentionimage-classificationImage ClassificationSimilar Papers 제목 키워드 기반
DREAM: Adaptive Reinforcement Learning based on Attention Mechanism for Temporal Knowledge Graph Reasoning
Temporal knowledge graphs (TKGs) model the temporal evolution of events and have recently attracted increasing attention. Since TKGs are intrinsically incomplete, it is necessary to reason out missing elements. Although …
Knowledge GraphsMissing Elementsreinforcement-learningReinforcement Learning+2On Explainability of Graph Neural Networks via Subgraph Explorations
We consider the problem of explaining the predictions of graph neural networks (GNNs), which otherwise are considered as black boxes. Existing methods invariably focus on explaining the importance of graph nodes or edges…
Explainability in Graph Neural Networks: A Taxonomic Survey
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 circumven…
SurveyExplainability in Machine Learning: a Pedagogical Perspective
Given the importance of integrating of explainability into machine learning, at present, there are a lack of pedagogical resources exploring this. Specifically, we have found a need for resources in explaining how one ca…
BIG-bench Machine LearningDecision MakingExplainability in Graph Neural Networks: An Experimental Survey
Graph neural networks (GNNs) have been extensively developed for graph representation learning in various application domains. However, similar to all other neural networks models, GNNs suffer from the black-box problem …
Graph Representation LearningRepresentation LearningSurvey