mlsanityData to 7 Oct 2026

GENEOnet: Statistical analysis supporting explainability and trustworthiness

arXiv 2503.09199 ↗First posted 12 Mar 2025cs.LG cs.AI q-bio.BMcited by 0

Not on the map. Why?

Abstract (arXiv)

Group Equivariant Non-Expansive Operators (GENEOs) have emerged as mathematical tools for constructing networks for Machine Learning and Artificial Intelligence. Recent findings suggest that such models can be inserted within the domain of eXplainable Artificial Intelligence (XAI) due to their inherent interpretability. In this study, we aim to verify this claim with respect to GENEOnet, a GENEO network developed for an application in computational biochemistry by employing various statistical analyses and experiments. Such experiments first allow us to perform a sensitivity analysis on GENEOnet's parameters to test their significance. Subsequently, we show that GENEOnet exhibits a significantly higher proportion of equivariance compared to other methods. Lastly, we demonstrate that GENEOnet is on average robust to perturbations arising from molecular dynamics. These results collectively serve as proof of the explainability, trustworthiness, and robustness of GENEOnet and confirm the beneficial use of GENEOs in the context of Trustworthy Artificial Intelligence.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 14 of its 67 references that are in the map. First posted on arXiv 12 Mar 2025.

Builds on

14 of 67 references.

References · 14

  1. 2017A Unified Approach to Interpreting Model Predictionscited by 6,488
  2. 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,040
  3. 2016Group Equivariant Convolutional Networkscited by 1,154
  4. 2018Weisfeiler and Leman Go Neural: Higher-order Graph Neural Networkscited by 878
  5. 2016Steerable CNNscited by 298
  6. 2016Harmonic Networks: Deep Translation and Rotation Equivariancecited by 293
  7. 2018Strike (with) a Pose: Neural Networks Are Easily Fooled by Strange Poses of Familiar Objectscited by 143
  8. 2018Towards a topological-geometrical theory of group equivariant non-expansive operators for data analysis and machine learningcited by 24
  9. 2019Improving detection of protein-ligand binding sites with 3D segmentationcited by 15
  10. 2020On the finite representation of group equivariant operators via permutant measurescited by 7
  11. 2022Generalized Permutants and Graph GENEOscited by 5
  12. 2024A novel approach to graph distinction through GENEOs and permutantscited by 4
2 more
  1. 2023Low-Resource White-Box Semantic Segmentation of Supporting Towers on 3D Point Clouds via Signature Shape Identificationcited by 2
  2. 2023A topological model for partial equivariance in deep learning and data analysiscited by 1

Built on by

Not cited yet.