mlsanityData to 14 Oct 2026

Learning with Category-Equivariant Architectures for Human Activity Recognition

arXiv 2511.01139 ↗First posted 3 Nov 2025cs.CV cs.AI cs.HCcited by 3

Not on the map. Why?

Abstract (arXiv)

We propose CatEquiv, a category-equivariant neural network for Human Activity Recognition (HAR) from inertial sensors that systematically encodes temporal, amplitude, and structural symmetries. We introduce a symmetry category that jointly represents cyclic time shifts, positive gain scalings, and the sensor-hierarchy poset, capturing the categorical symmetry structure of the data. CatEquiv achieves equivariance with respect to the categorical symmetry product. On UCI-HAR under out-of-distribution perturbations, CatEquiv attains markedly higher robustness compared with circularly padded CNNs and plain CNNs. These results demonstrate that enforcing categorical symmetries yields strong invariance and generalization without additional model capacity.

Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Builds on 19 of its 24 references that are in the map. First posted on arXiv 3 Nov 2025.

Builds on

19 of 24 references.

References · 19

  1. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 7,005
  2. 2016Layer Normalizationcited by 5,669
  3. 2019Benchmarking Neural Network Robustness to Common Corruptions and Perturbationscited by 2,877
  4. 2018Group Normalizationcited by 1,524
  5. 2021Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gaugescited by 1,167
  6. 2016Group Equivariant Convolutional Networkscited by 1,165
  7. 2021E(n) Equivariant Graph Neural Networkscited by 965
  8. 2018Tensor field networks: Rotation- and translation-equivariant neural networks for 3D point cloudscited by 746
  9. 2020SE(3)-Transformers: 3D Roto-Translation Equivariant Attention Networkscited by 607
  10. 2018Spherical CNNscited by 456
  11. 2019General E(2)-Equivariant Steerable CNNscited by 446
  12. 2018Invariant and Equivariant Graph Networkscited by 346
7 more
  1. 2016Steerable CNNscited by 305
  2. 2018On the Generalization of Equivariance and Convolution in Neural Networks to the Action of Compact Groupscited by 300
  3. 2016Harmonic Networks: Deep Translation and Rotation Equivariancecited by 295
  4. 2019Cormorant: Covariant Molecular Neural Networkscited by 263
  5. 2017Learning SO(3) Equivariant Representations with Spherical CNNscited by 248
  6. 2017Equivariance Through Parameter-Sharingcited by 141
  7. 2016Rotation equivariant vector field networkscited by 99

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 1; 2026: 2.

3 papers.

  1. 2025Categorical Equivariant Deep Learning: Category-Equivariant Neural Networks and Universal Approximation Theoremscited by 4
  2. 2026Foundations of Equivariant Deep Learning: Unifying Graph and Sheaf Neural Networkscited by 1
  3. 2026Capturing Cardiac Cyclicity through Phase-Equivariant Self-Supervised Learningcited by 0