17 citations · 18 across the 4 of their papers we have counts for
4 papers · 1 filter
SliceGX: Layer-wise GNN Explanation with Model-slicing
Tingting Zhu, Tingyang Chen, Yinghui Wu +2
Ensuring the trustworthiness of graph neural networks (GNNs), which are often treated as black-box models, requires effective explanation techniques. Existing GNN explanations typi…
Interpreting Graph Inference with Skyline Explanations
Dazhuo Qiu, Haolai Che, Arijit Khan +1
Inference queries have been routinely issued to graph machine learning models such as graph neural networks (GNNs) for various network analytical tasks. Nevertheless, GNN outputs a…
Generating Robust Counterfactual Witnesses for Graph Neural Networks
Dazhuo Qiu, Mengying Wang, Arijit Khan +1
This paper introduces a new class of explanation structures, called robust counterfactual witnesses (RCWs), to provide robust, both counterfactual and factual explanations for grap…
View-based Explanations for Graph Neural Networks
Tingyang Chen, Dazhuo Qiu, Yinghui Wu +3
Generating explanations for graph neural networks (GNNs) has been studied to understand their behavior in analytical tasks such as graph classification. Existing approaches aim to…