mlsanityData to 14 Oct 2026

Symmetry-Preserving Paths in Integrated Gradients

arXiv 2103.13533 ↗First posted 25 Mar 2021cs.LG cs.AIcited by 4

Not on the map. Why?

Abstract (arXiv)

We provide rigorous proofs that the Integrated Gradients (IG) attribution method for deep networks satisfies completeness and symmetry-preserving properties. We also study the uniqueness of IG as a path method preserving symmetry.

Key facts. Cited by 4 papers in the map (data through 14 Oct 2026). Builds on 2 of its 5 references that are in the map. First posted on arXiv 25 Mar 2021.

Builds on

2 of 5 references.

References · 2

  1. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
  2. 2017Axiomatic Attribution for Deep Networkscited by 3,384

Built on by

Cited by year

Citing papers per year: 2022: 2; 2023: 1; 2024: 1.

4 papers.

  1. 2022Impossibility Theorems for Feature Attributioncited by 78
  2. 2022A Rigorous Study of Integrated Gradients Method and Extensions to Internal Neuron Attributionscited by 64
  3. 2024Gradient based Feature Attribution in Explainable AI: A Technical Reviewcited by 34
  4. 2023Four Axiomatic Characterizations of the Integrated Gradients Attribution Methodcited by 5