mlsanityData to 14 Oct 2026

Equivariant Mesh Attention Networks

arXiv 2205.10662 ↗First posted 21 May 2022cs.LG cs.CV stat.MLcited by 12

Not on the map. Why?

Abstract (arXiv)

Equivariance to symmetries has proven to be a powerful inductive bias in deep learning research. Recent works on mesh processing have concentrated on various kinds of natural symmetries, including translations, rotations, scaling, node permutations, and gauge transformations. To date, no existing architecture is equivariant to all of these transformations. In this paper, we present an attention-based architecture for mesh data that is provably equivariant to all transformations mentioned above. Our pipeline relies on the use of relative tangential features: a simple, effective, equivariance-friendly alternative to raw node positions as inputs. Experiments on the FAUST and TOSCA datasets confirm that our proposed architecture achieves improved performance on these benchmarks and is indeed equivariant, and therefore robust, to a wide variety of local/global transformations.

Key facts. Cited by 12 papers in the map (data through 14 Oct 2026). Builds on 34 of its 45 references that are in the map. First posted on arXiv 21 May 2022.

Builds on

34 of 45 references.

References · 34

  1. 2017Attention Is All You Needcited by 60,361
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  3. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  4. 2020Language Models are Few-Shot Learnerscited by 32,419
  5. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  6. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
  7. 2017Graph Attention Networkscited by 8,923
  8. 2016Convolutional Neural Networks on Graphs with Fast Localized Spectral Filteringcited by 2,089
  9. 2021Decision Transformer: Reinforcement Learning via Sequence Modelingcited by 1,546
  10. 2017Deep Setscited by 1,421
  11. 2021Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gaugescited by 1,167
  12. 2016Group Equivariant Convolutional Networkscited by 1,165
22 more
  1. 2021Perceiver: General Perception with Iterative Attentioncited by 1,104
  2. 2013Spectral Networks and Locally Connected Networks on Graphscited by 1,102
  3. 2021E(n) Equivariant Graph Neural Networkscited by 965
  4. 2018Tensor field networks: Rotation- and translation-equivariant neural networks for 3D point cloudscited by 746
  5. 2020SE(3)-Transformers: 3D Roto-Translation Equivariant Attention Networkscited by 607
  6. 2020Masked Label Prediction: Unified Message Passing Model for Semi-Supervised Classificationcited by 506
  7. 2018Spherical CNNscited by 456
  8. 2019General E(2)-Equivariant Steerable CNNscited by 446
  9. 2018Rotation Equivariant CNNs for Digital Pathologycited by 422
  10. 2020Self-supervised Equivariant Attention Mechanism for Weakly Supervised Semantic Segmentationcited by 300
  11. 2019Gauge Equivariant Convolutional Networks and the Icosahedral CNNcited by 267
  12. 2021GRAND: Graph Neural Diffusioncited by 258
  13. 2020Equivariant Flows: Exact Likelihood Generative Learning for Symmetric Densitiescited by 250
  14. 2017Learning Steerable Filters for Rotation Equivariant CNNscited by 194
  15. 2019Universal Invariant and Equivariant Graph Neural Networkscited by 183
  16. 2019Scale-Equivariant Steerable Networkscited by 110
  17. 2020LieTransformer: Equivariant self-attention for Lie Groupscited by 100
  18. 2020Gauge Equivariant Mesh CNNs: Anisotropic convolutions on geometric graphscited by 92
  19. 2019SpiralNet++: A Fast and Highly Efficient Mesh Convolution Operatorcited by 89
  20. 2021Coordinate Independent Convolutional Networks -- Isometry and Gauge Equivariant Convolutions on Riemannian Manifoldscited by 73
  21. 2020Group Equivariant Stand-Alone Self-Attention For Visioncited by 63
  22. 2017Deep Rotation Equivariant Networkcited by 16

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 2; 2023: 3; 2024: 4; 2025: 1; 2026: 2.

12 papers.

  1. 2022Explaining the Explainers in Graph Neural Networks: a Comparative Studycited by 35
  2. 2022Equi-Tuning: Group Equivariant Fine-Tuning of Pretrained Modelscited by 22
  3. 2023Efficient Equivariant Transfer Learning from Pretrained Modelscited by 11
  4. 2024E(3)-Equivariant Mesh Neural Networkscited by 9
  5. 2023Modeling Dynamics over Meshes with Gauge Equivariant Nonlinear Message Passingcited by 3
  6. 2024Link Prediction with Untrained Message Passing Layerscited by 3
  7. 2024Current Symmetry Group Equivariant Convolution Frameworks for Representation Learningcited by 2
  8. 2025AdS-GNN -- a Conformally Equivariant Graph Neural Networkcited by 2
  9. 2023Efficient Model-Agnostic Multi-Group Equivariant Networkscited by 1
  10. 2024LMSeg: An end-to-end geometric message-passing network on barycentric dual graphs for large-scale landscape mesh segmentationcited by 0
  11. 2026Smoothness Errors in Dynamics Models and How to Avoid Themcited by 0
  12. 2026Augmented Equivariant Mesh Networks for Anatomical Segmentationcited by 0