mlsanityData to 7 Oct 2026

Equivariant Matrix Function Neural Networks

arXiv 2310.10434 ↗First posted 16 Oct 2023stat.ML cond-mat.mtrl-sci cs.LGcited by 3

Not on the map. Why?

Abstract (arXiv)

Graph Neural Networks (GNNs), especially message-passing neural networks (MPNNs), have emerged as powerful architectures for learning on graphs in diverse applications. However, MPNNs face challenges when modeling non-local interactions in graphs such as large conjugated molecules, and social networks due to oversmoothing and oversquashing. Although Spectral GNNs and traditional neural networks such as recurrent neural networks and transformers mitigate these challenges, they often lack generalizability, or fail to capture detailed structural relationships or symmetries in the data. To address these concerns, we introduce Matrix Function Neural Networks (MFNs), a novel architecture that parameterizes non-local interactions through analytic matrix equivariant functions. Employing resolvent expansions offers a straightforward implementation and the potential for linear scaling with system size. The MFN architecture achieves stateof-the-art performance in standard graph benchmarks, such as the ZINC and TU datasets, and is able to capture intricate non-local interactions in quantum systems, paving the way to new state-of-the-art force fields.

Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 55 of its 87 references that are in the map. First posted on arXiv 16 Oct 2023.

Builds on

55 of 87 references.

References · 55

  1. 2017Attention Is All You Needcited by 59,932
  2. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  3. 2017Graph Attention Networkscited by 8,854
  4. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 6,979
  5. 2017Inductive Representation Learning on Large Graphscited by 6,284
  6. 2016Layer Normalizationcited by 5,579
  7. 2018How Powerful are Graph Neural Networks?cited by 4,355
  8. 2017Neural Message Passing for Quantum Chemistrycited by 3,460
  9. 2019A Comprehensive Survey on Graph Neural Networkscited by 2,906
  10. 2016Convolutional Neural Networks on Graphs with Fast Localized Spectral Filteringcited by 2,085
  11. 2018Relational inductive biases, deep learning, and graph networkscited by 1,341
  12. 2014On the Properties of Neural Machine Translation: Encoder-Decoder Approachescited by 1,303
38 more
  1. 2021Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gaugescited by 1,131
  2. 2018Self-Attention with Relative Position Representationscited by 1,112
  3. 2018Predict then Propagate: Graph Neural Networks meet Personalized PageRankcited by 987
  4. 2021E(n) Equivariant Graph Neural Networkscited by 951
  5. 2018Weisfeiler and Leman Go Neural: Higher-order Graph Neural Networkscited by 878
  6. 2021E(3)-Equivariant Graph Neural Networks for Data-Efficient and Accurate Interatomic Potentialscited by 701
  7. 2020Benchmarking Graph Neural Networkscited by 672
  8. 2020Adaptive Universal Generalized PageRank Graph Neural Networkcited by 592
  9. 2013Generating Sequences With Recurrent Neural Networkscited by 549
  10. 2021Rethinking Graph Transformers with Spectral Attentioncited by 468
  11. 2022MACE: Higher Order Equivariant Message Passing Neural Networks for Fast and Accurate Force Fieldscited by 467
  12. 2018Spherical CNNscited by 452
  13. 2019Provably Powerful Graph Networkscited by 385
  14. 2018Invariant and Equivariant Graph Networkscited by 339
  15. 2021Do Transformers Really Perform Bad for Graph Representation?cited by 318
  16. 2016Learning Convolutional Neural Networks for Graphscited by 314
  17. 2017Dynamic Edge-Conditioned Filters in Convolutional Neural Networks on Graphscited by 307
  18. 2016Steerable CNNscited by 298
  19. 2018On the Generalization of Equivariance and Convolution in Neural Networks to the Action of Compact Groupscited by 296
  20. 2019Cormorant: Covariant Molecular Neural Networkscited by 262
  21. 2021Geometric and Physical Quantities Improve E(3) Equivariant Message Passingcited by 225
  22. 2020Machine Learning Force Fieldscited by 204
  23. 2021BernNet: Learning Arbitrary Graph Spectral Filters via Bernstein Approximationcited by 195
  24. 2019Graph Neural Networks with convolutional ARMA filterscited by 185
  25. 2022How Powerful are Spectral Graph Neural Networkscited by 169
  26. 2023On Over-Squashing in Message Passing Neural Networks: The Impact of Width, Depth, and Topologycited by 163
  27. 2021Interpreting and Unifying Graph Neural Networks with An Optimization Frameworkcited by 131
  28. 2021SpookyNet: Learning Force Fields with Electronic Degrees of Freedom and Nonlocal Effectscited by 103
  29. 2022The Design Space of E(3)-Equivariant Atom-Centered Interatomic Potentialscited by 100
  30. 2023On the Expressive Power of Geometric Graph Neural Networkscited by 89
  31. 2014Propagation Kernelscited by 88
  32. 2019Unifying machine learning and quantum chemistry -- a deep neural network for molecular wavefunctionscited by 73
  33. 2021SE(3)-equivariant prediction of molecular wavefunctions and electronic densitiescited by 67
  34. 2018Anonymous Walk Embeddingscited by 46
  35. 2023Ewald-based Long-Range Message Passing for Molecular Graphscited by 46
  36. 2022So3krates: Equivariant attention for interactions on arbitrary length-scales in molecular systemscited by 39
  37. 2020Natural Graph Networkscited by 35
  38. 2023Evaluation of the MACE Force Field Architecture: from Medicinal Chemistry to Materials Sciencecited by 25

50 most cited of 55 All 55 (JSON)

Built on by

Cited by year

Citing papers per year: 2024: 3.

3 papers.

  1. 2024Spatio-Spectral Graph Neural Networkscited by 17
  2. 2024Euclidean Fast Attention -- Machine Learning Global Atomic Representations at Linear Costcited by 12
  3. 2024Unitary convolutions for learning on graphs and groupscited by 8