English

Symmetry-Preserving Paths in Integrated Gradients

Machine Learning 2021-03-26 v1 Artificial Intelligence

Abstract

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.

Cite

@article{arxiv.2103.13533,
  title  = {Symmetry-Preserving Paths in Integrated Gradients},
  author = {Miguel Lerma and Mirtha Lucas},
  journal= {arXiv preprint arXiv:2103.13533},
  year   = {2021}
}

Comments

7 pages, 1 figure

R2 v1 2026-06-24T00:32:12.050Z