Riemannian Integrated Gradients: A Geometric View of Explainable AI
Not on the map. Why?
Abstract (arXiv)
We introduce Riemannian Integrated Gradients (RIG); an extension of Integrated Gradients (IG) to Riemannian manifolds. We demonstrate that RIG restricts to IG when the Riemannian manifold is Euclidean space. We show that feature attribution can be phrased as an eigenvalue problem where attributions correspond to eigenvalues of a symmetric endomorphism.
Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 9 of its 16 references that are in the map. First posted on arXiv 2 Mar 2025.
Builds on
9 of 16 references.
References · 9
- 2017Axiomatic Attribution for Deep Networkscited by 3,350
- 2017SmoothGrad: removing noise by adding noisecited by 1,097
- 2018Hyperbolic Neural Networkscited by 393
- 2017The Riemannian Geometry of Deep Generative Modelscited by 81
- 2022A Rigorous Study of Integrated Gradients Method and Extensions to Internal Neuron Attributionscited by 64
- 2022Statistical exploration of the Manifold Hypothesiscited by 29
- 2024Manifold Integrated Gradients: Riemannian Geometry for Feature Attributioncited by 21
- 2022The Manifold Hypothesis for Gradient-Based Explanationscited by 15
- 2024Algebraic Adversarial Attacks on Integrated Gradientscited by 4
Built on by
Citing papers per year: 2025: 2.
2 papers.