paper-with-me

홈 › Papers

Mathematical Foundation of Interpretable Equivariant Surrogate Models

2025-03-03 · Jacopo Joy Colombini, Filippo Bonchi, Francesco Giannini, Fosca Giannotti, Roberto Pellungrini, Patrizio Frosini

This paper introduces a rigorous mathematical framework for neural network explainability, and more broadly for the explainability of equivariant operators called Group Equivariant Operators (GEOs) based on Group Equivariant Non-Expansive Operators (GENEOs) transformations. The central concept involves quantifying the distance between GEOs by measuring the non-commutativity of specific diagrams. Additionally, the paper proposes a definition of interpretability of GEOs according to a complexity measure that can be defined according to each user preferences. Moreover, we explore the formal properties of this framework and show how it can be applied in classical machine learning scenarios, like image classification with convolutional neural networks.

📄 PDF Abstract BibTeX arXiv:2503.01942

Code (0)

등록된 구현이 없습니다.

Tasks

image-classificationImage Classification

Similar Papers 제목 키워드 기반

Robust and Interpretable Adaptation of Equivariant Materials Foundation Models via Sparsity-promoting Fine-tuning

2026-06-17 · Youngwoo Cho, Seunghoon Yi, Wooil Yang, Sungmo Kang 외 arxiv

Pre-trained materials foundation models, or machine learning interatomic potentials, leverage general physicochemical knowledge to effectively approximate potential energy surfaces. However, they often require domain-spe…

Geometric Deep Learning and Equivariant Neural Networks

2021-05-28 · Jan E. Gerken, Jimmy Aronsson, Oscar Carlsson, Hampus Linander 외

We survey the mathematical foundations of geometric deep learning, focusing on group equivariant and gauge equivariant neural networks. We develop gauge equivariant convolutional neural networks on arbitrary manifolds $\…

Deep Learningobject-detectionObject DetectionSemantic Segmentation

Pretrain on Small Synthetic Data, Scale Large for Free: Symmetry-Aware Foundation Model for Logic Rule Induction

2026-08-01 · Yin Jun Phua arxiv

Logical rule induction seeks interpretable rules that transfer across propositional schemas. This requires respecting symmetries: atom naming, example order, polarity flips, and label swap. Enforcing exact symmetry by co…

A Complete Guide to Spherical Equivariant Graph Transformers

2025-12-15 · Sophia Tang arxiv

Spherical equivariant graph neural networks (EGNNs) provide a principled framework for learning on three-dimensional molecular and biomolecular systems, where predictions must respect the rotational symmetries inherent i…

Molecular Property Prediction

Symmetry Group Equivariant Architectures for Physics

2022-03-11 · Alexander Bogatskiy, Sanmay Ganguly, Thomas Kipf, Risi Kondor 외

Physical theories grounded in mathematical symmetries are an essential component of our understanding of a wide range of properties of the universe. Similarly, in the domain of machine learning, an awareness of symmetrie…

BIG-bench Machine Learning