mlsanityData to 14 Oct 2026

Graph-based Integrated Gradients for Explaining Graph Neural Networks

arXiv 2509.07648 ↗First posted 9 Sep 2025cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 15 of its 30 references that are in the map. First posted on arXiv 9 Sep 2025.

Builds on

15 of 30 references.

References · 15

  1. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
  2. 2017Axiomatic Attribution for Deep Networkscited by 3,384
  3. 2021Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gaugescited by 1,167
  4. 2020Explainability in Graph Neural Networks: A Taxonomic Surveycited by 384
  5. 2017The (Un)reliability of saliency methodscited by 333
  6. 2022Evaluating Explainability for Graph Neural Networkscited by 87
  7. 2022A Rigorous Study of Integrated Gradients Method and Extensions to Internal Neuron Attributionscited by 64
  8. 2019Community Detection on Networks with Ricci Flowcited by 62
  9. 2021Discretized Integrated Gradients for Explaining Language Modelscited by 46
  10. 2022Statistical exploration of the Manifold Hypothesiscited by 29
  11. 2024Manifold Integrated Gradients: Riemannian Geometry for Feature Attributioncited by 21
  12. 2022The Manifold Hypothesis for Gradient-Based Explanationscited by 16
3 more
  1. 2024Algebraic Adversarial Attacks on Integrated Gradientscited by 4
  2. 2025Tangentially Aligned Integrated Gradients for User-Friendly Explanationscited by 3
  3. 2025Riemannian Integrated Gradients: A Geometric View of Explainable AIcited by 2

Built on by

Not cited yet.