{"ID":2873012,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2509.07648","arxiv_id":"2509.07648","title":"Graph-based Integrated Gradients for Explaining Graph Neural Networks","abstract":"Integrated Gradients (IG) is a common explainability technique to address the black-box problem of neural networks. Integrated gradients assumes continuous data. Graphs are discrete structures making IG ill-suited to graphs. In this work, we introduce graph-based integrated gradients (GB-IG); an extension of IG to graphs. We demonstrate on four synthetic datasets that GB-IG accurately identifies crucial structural components of the graph used in classification tasks. We further demonstrate on three prevalent real-world graph datasets that GB-IG outperforms IG in highlighting important features for node classification tasks.","short_abstract":"Integrated Gradients (IG) is a common explainability technique to address the black-box problem of neural networks. Integrated gradients assumes continuous data. Graphs are discrete structures making IG ill-suited to graphs. In this work, we introduce graph-based integrated gradients (GB-IG); an extension of IG to grap...","url_abs":"https://arxiv.org/abs/2509.07648","url_pdf":"https://arxiv.org/pdf/2509.07648v1","authors":"[\"Lachlan Simpson\",\"Kyle Millar\",\"Adriel Cheng\",\"Cheng-Chew Lim\",\"Hong Gunn Chew\"]","published":"2025-09-09T12:15:25Z","proceeding":"cs.LG","tasks":"[\"cs.LG\"]","methods":"[\"Graph Neural Network\"]","has_code":false}