mlsanityData to 7 Oct 2026

GNN-VPA: A Variance-Preserving Aggregation Strategy for Graph Neural Networks

arXiv 2403.04747 ↗First posted 7 Mar 2024cs.LG cs.AI stat.MLcited by 5

Not on the map. Why?

Abstract (arXiv)

Graph neural networks (GNNs), and especially message-passing neural networks, excel in various domains such as physics, drug discovery, and molecular modeling. The expressivity of GNNs with respect to their ability to discriminate non-isomorphic graphs critically depends on the functions employed for message aggregation and graph-level readout. By applying signal propagation theory, we propose a variance-preserving aggregation function (VPA) that maintains expressivity, but yields improved forward and backward dynamics. Experiments demonstrate that VPA leads to increased predictive performance for popular GNN architectures as well as improved learning dynamics. Our results could pave the way towards normalizer-free or self-normalizing GNNs.

Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Builds on 38 of its 49 references that are in the map. First posted on arXiv 7 Mar 2024.

Builds on

38 of 49 references.

References · 38

  1. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  2. 2017Graph Attention Networkscited by 8,854
  3. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 6,979
  4. 2017Inductive Representation Learning on Large Graphscited by 6,284
  5. 2016Layer Normalizationcited by 5,579
  6. 2018How Powerful are Graph Neural Networks?cited by 4,355
  7. 2015Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classificationcited by 3,590
  8. 2017Neural Message Passing for Quantum Chemistrycited by 3,460
  9. 2019A Comprehensive Survey on Graph Neural Networkscited by 2,906
  10. 2019Fast Graph Representation Learning with PyTorch Geometriccited by 2,414
  11. 2016Convolutional Neural Networks on Graphs with Fast Localized Spectral Filteringcited by 2,085
  12. 2017Modeling Relational Data with Graph Convolutional Networkscited by 1,684
26 more
  1. 2019Simplifying Graph Convolutional Networkscited by 1,470
  2. 2021Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gaugescited by 1,131
  3. 2021E(n) Equivariant Graph Neural Networkscited by 951
  4. 2018Weisfeiler and Leman Go Neural: Higher-order Graph Neural Networkscited by 878
  5. 2020Learning to Simulate Complex Physics with Graph Networkscited by 867
  6. 2015Convolutional Networks on Graphs for Learning Molecular Fingerprintscited by 751
  7. 2020TUDataset: A collection of benchmark datasets for learning with graphscited by 718
  8. 2019Graph Neural Networks for Social Recommendationcited by 711
  9. 2017Deep Neural Networks as Gaussian Processescited by 617
  10. 2017Self-Normalizing Neural Networkscited by 591
  11. 2020Principal Neighbourhood Aggregation for Graph Netscited by 477
  12. 2019Self-Attention Graph Poolingcited by 421
  13. 2022Message Passing Neural PDE Solverscited by 368
  14. 2021Combinatorial optimization and reasoning with graph neural networkscited by 267
  15. 2022GraphCast: Learning skillful medium-range global weather forecastingcited by 261
  16. 2016Molecular Graph Convolutions: Moving Beyond Fingerprintscited by 238
  17. 2016Deep Information Propagationcited by 194
  18. 2022Graph neural networks for materials science and chemistrycited by 181
  19. 2022Forecasting Global Weather with Graph Neural Networkscited by 165
  20. 2019Fake News Detection on Social Media using Geometric Deep Learningcited by 115
  21. 2021Rapid training of deep neural networks without skip connections or normalization layers using Deep Kernel Shapingcited by 51
  22. 2021Boundary Graph Neural Networks for 3D Simulationscited by 24
  23. 2023Variational Annealing on Graphs for Combinatorial Optimizationcited by 21
  24. 2021Distribution Knowledge Embedding for Graph Poolingcited by 19
  25. 2023Principled Weight Initialisation for Input-Convex Neural Networkscited by 12
  26. 2020Bidirectionally Self-Normalizing Neural Networkscited by 3

Built on by

Cited by year

Citing papers per year: 2024: 2; 2025: 3.

5 papers.

  1. 2024SemlaFlow -- Efficient 3D Molecular Generation with Latent Attention and Equivariant Flow Matchingcited by 40
  2. 2025Scalable Discrete Diffusion Samplers: Combinatorial Optimization and Statistical Physicscited by 28
  3. 2025Space Group Equivariant Crystal Diffusioncited by 15
  4. 2024Sequential Signal Mixing Aggregation for Message Passing Graph Neural Networkscited by 3
  5. 2025BioX-CPath: Biologically-driven Explainable Diagnostics for Multistain IHC Computational Pathologycited by 1