mlsanityData to 7 Oct 2026

Expressive Sign Equivariant Networks for Spectral Geometric Learning

arXiv 2312.02339 ↗First posted 4 Dec 2023cs.LG cs.AI stat.MLcited by 15

Not on the map. Why?

Abstract (arXiv)

Recent work has shown the utility of developing machine learning models that respect the structure and symmetries of eigenvectors. These works promote sign invariance, since for any eigenvector v the negation -v is also an eigenvector. However, we show that sign invariance is theoretically limited for tasks such as building orthogonally equivariant models and learning node positional encodings for link prediction in graphs. In this work, we demonstrate the benefits of sign equivariance for these tasks. To obtain these benefits, we develop novel sign equivariant neural network architectures. Our models are based on a new analytic characterization of sign equivariant polynomials and thus inherit provable expressiveness properties. Controlled synthetic experiments show that our networks can achieve the theoretically predicted benefits of sign equivariant models. Code is available at https://github.com/cptq/Sign-Equivariant-Nets.

Key facts. Cited by 15 papers in the map (data through 7 Oct 2026). Builds on 64 of its 83 references that are in the map. First posted on arXiv 4 Dec 2023.

Builds on

64 of 83 references.

References · 64

  1. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  2. 2017Graph Attention Networkscited by 8,854
  3. 2018How Powerful are Graph Neural Networks?cited by 4,355
  4. 2017Neural Message Passing for Quantum Chemistrycited by 3,460
  5. 2020Open Graph Benchmark: Datasets for Machine Learning on Graphscited by 2,148
  6. 2017Deep Setscited by 1,394
  7. 2016Group Equivariant Convolutional Networkscited by 1,154
  8. 2021Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gaugescited by 1,131
  9. 2021E(n) Equivariant Graph Neural Networkscited by 951
  10. 2018Link Prediction Based on Graph Neural Networkscited by 829
  11. 2018Tensor field networks: Rotation- and translation-equivariant neural networks for 3D point cloudscited by 735
  12. 2022Recipe for a General, Powerful, Scalable Graph Transformercited by 702
38 more
  1. 2020Benchmarking Graph Neural Networkscited by 672
  2. 2020SE(3)-Transformers: 3D Roto-Translation Equivariant Attention Networkscited by 602
  3. 2021Rethinking Graph Transformers with Spectral Attentioncited by 468
  4. 20183D Steerable CNNs: Learning Rotationally Equivariant Features in Volumetric Datacited by 348
  5. 2017Residual Gated Graph ConvNetscited by 341
  6. 2018Neural Relational Inference for Interacting Systemscited by 339
  7. 2018Invariant and Equivariant Graph Networkscited by 339
  8. 2021Graph Neural Networks with Learnable Structural and Positional Representationscited by 326
  9. 2017Community Detection and Stochastic Block Modelscited by 317
  10. 2021Vector Neurons: A General Framework for SO(3)-Equivariant Networkscited by 304
  11. 2016Steerable CNNscited by 298
  12. 2018On the Generalization of Equivariance and Convolution in Neural Networks to the Action of Compact Groupscited by 296
  13. 2021Neural Bellman-Ford Networks: A General Graph Neural Network Framework for Link Predictioncited by 273
  14. 2019Cormorant: Covariant Molecular Neural Networkscited by 262
  15. 2020Equivariant Flows: Exact Likelihood Generative Learning for Symmetric Densitiescited by 248
  16. 2020Can Graph Neural Networks Count Substructures?cited by 235
  17. 2017Network Embedding as Matrix Factorization: Unifying DeepWalk, LINE, PTE, and node2veccited by 197
  18. 2021Identity-aware Graph Neural Networkscited by 197
  19. 2022Structure-Aware Transformer for Graph Representation Learningcited by 191
  20. 2020The Surprising Power of Graph Neural Networks with Random Node Initializationcited by 190
  21. 2022Pure Transformers are Powerful Graph Learnerscited by 188
  22. 2021A Practical Method for Constructing Equivariant Multilayer Perceptrons for Arbitrary Matrix Groupscited by 185
  23. 2022Sign and Basis Invariant Networks for Spectral Graph Representation Learningcited by 176
  24. 2021Frame Averaging for Invariant and Equivariant Network Designcited by 166
  25. 2019On the Universality of Invariant Networkscited by 151
  26. 2019Relational Pooling for Graph Representationscited by 150
  27. 2020Labeling Trick: A Theory of Using Graph Neural Networks for Multi-Node Representation Learningcited by 148
  28. 2021GraphiT: Encoding Graph Structure in Transformerscited by 146
  29. 2017Equivariance Through Parameter-Sharingcited by 139
  30. 2018Universal approximations of invariant maps by neural networkscited by 127
  31. 2021Scalars are universal: Equivariant machine learning, structured like classical physicscited by 127
  32. 2021Global Self-Attention as a Replacement for Graph Convolutioncited by 113
  33. 2022Equivariance with Learned Canonicalization Functionscited by 106
  34. 2020On Learning Sets of Symmetric Elementscited by 97
  35. 2022Equivariant and Stable Positional Encoding for More Powerful Graph Neural Networkscited by 94
  36. 2022A Generalization of ViT/MLP-Mixer to Graphscited by 93
  37. 2022Graph Neural Networks for Link Prediction with Subgraph Sketchingcited by 81
  38. 2023Attending to Graph Transformerscited by 81

50 most cited of 64 All 64 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 1; 2024: 9; 2025: 4; 2026: 1.

15 papers.

Sort:

By area:

  1. 2024A Canonicalization Perspective on Invariant and Equivariant Learningcited by 25
  2. 2023Symmetry Breaking and Equivariant Neural Networkscited by 24
  3. 2024Scale Equivariant Graph Metanetworkscited by 23
  4. 2024Equivariance via Minimal Frame Averaging for More Symmetries and Efficiencycited by 18
  5. 2025Improving Equivariant Networks with Probabilistic Symmetry Breakingcited by 15
  6. 2024What Are Good Positional Encodings for Directed Graphs?cited by 7
  7. 2024Homomorphism Counts as Structural Encodings for Graph Learningcited by 6
  8. 2024Future Directions in the Theory of Graph Machine Learningcited by 5
  9. 2024Stiefel Flow Matching for Moment-Constrained Structure Elucidationcited by 5
  10. 2025Balancing Efficiency and Expressiveness: Subgraph GNNs with Walk-Based Centralitycited by 5
  11. 2024Rethinking Spectral Graph Neural Networks with Spatially Adaptive Filteringcited by 3
  12. 2025Adaptive Canonicalization with Application to Invariant Anisotropic Geometric Networkscited by 3
3 more
  1. 2024Equivariant Machine Learning on Graphs with Nonlinear Spectral Filterscited by 2
  2. 2025SESaMo: Symmetry-Enforcing Stochastic Modulation for Normalizing Flowscited by 2
  3. 2026Edge-Level Automorphism in GNNs: A Quantitative Framework and Effective Designs For Link Predictioncited by 0