BAGEL: A Benchmark for Assessing Graph Neural Network Explanations
Reviewed by Pith T0 review T1 audit T2 compute T3 formal T4 reserved pith:HTKXW522record.jsonopen to challenge →
read the original abstract
The problem of interpreting the decisions of machine learning is a well-researched and important. We are interested in a specific type of machine learning model that deals with graph data called graph neural networks. Evaluating interpretability approaches for graph neural networks (GNN) specifically are known to be challenging due to the lack of a commonly accepted benchmark. Given a GNN model, several interpretability approaches exist to explain GNN models with diverse (sometimes conflicting) evaluation methodologies. In this paper, we propose a benchmark for evaluating the explainability approaches for GNNs called Bagel. In Bagel, we firstly propose four diverse GNN explanation evaluation regimes -- 1) faithfulness, 2) sparsity, 3) correctness. and 4) plausibility. We reconcile multiple evaluation metrics in the existing literature and cover diverse notions for a holistic evaluation. Our graph datasets range from citation networks, document graphs, to graphs from molecules and proteins. We conduct an extensive empirical study on four GNN models and nine post-hoc explanation approaches for node and graph classification tasks. We open both the benchmarks and reference implementations and make them available at https://github.com/Mandeep-Rathee/Bagel-benchmark.
This paper has not been read by Pith yet.
Forward citations
Cited by 3 Pith papers
-
A method for the systematic generation of graph XAI benchmarks via Weisfeiler-Leman coloring
A systematic method leveraging Weisfeiler-Leman coloring to mine class-discriminating motifs as proxy explanations, enabling the creation of the OpenGraphXAI benchmark suite from real-world datasets.
-
xAI-Drop: Don't Use What You Cannot Explain
xAI-Drop introduces an explainability-based topological dropping regularizer for GNNs that outperforms state-of-the-art dropping methods in accuracy and explanation quality on real-world datasets.
-
Explaining the Explainers in Graph Neural Networks: a Comparative Study
Benchmark study of ten GNN explainers on eight architectures and six datasets that isolates usable components and issues practical recommendations.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.