mlsanityData to 7 Oct 2026

Using Random Noise Equivariantly to Boost Graph Neural Networks Universally

arXiv 2502.02479 ↗First posted 4 Feb 2025cs.LGcited by 2

Not on the map. Why?

Abstract (arXiv)

Recent advances in Graph Neural Networks (GNNs) have explored the potential of random noise as an input feature to enhance expressivity across diverse tasks. However, naively incorporating noise can degrade performance, while architectures tailored to exploit noise for specific tasks excel yet lack broad applicability. This paper tackles these issues by laying down a theoretical framework that elucidates the increased sample complexity when introducing random noise into GNNs without careful design. We further propose Equivariant Noise GNN (ENGNN), a novel architecture that harnesses the symmetrical properties of noise to mitigate sample complexity and bolster generalization. Our experiments demonstrate that using noise equivariantly significantly enhances performance on node-level, link-level, subgraph, and graph-level tasks and achieves comparable performance to models designed for specific tasks, thereby offering a general method to boost expressivity across various graph tasks.

Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 59 of its 70 references that are in the map. First posted on arXiv 4 Feb 2025.

Builds on

59 of 70 references.

References · 59

  1. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  2. 2017Inductive Representation Learning on Large Graphscited by 6,284
  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. 2016Convolutional Neural Networks on Graphs with Fast Localized Spectral Filteringcited by 2,085
  7. 2017Deep Setscited by 1,394
  8. 2018Deeper Insights into Graph Convolutional Networks for Semi-Supervised Learningcited by 1,099
  9. 2018Pitfalls of Graph Neural Network Evaluationcited by 994
  10. 2018Predict then Propagate: Graph Neural Networks meet Personalized PageRankcited by 987
  11. 2016Revisiting Semi-Supervised Learning with Graph Embeddingscited by 970
  12. 2018Link Prediction Based on Graph Neural Networkscited by 829
38 more
  1. 2020Geom-GCN: Geometric Graph Convolutional Networkscited by 821
  2. 2016Automatic chemical design using a data-driven continuous representation of moleculescited by 762
  3. 2022Recipe for a General, Powerful, Scalable Graph Transformercited by 702
  4. 2020On the Bottleneck of Graph Neural Networks and its Practical Implicationscited by 624
  5. 2020Adaptive Universal Generalized PageRank Graph Neural Networkcited by 592
  6. 2018FastGCN: Fast Learning with Graph Convolutional Networks via Importance Samplingcited by 583
  7. 2019Multi-scale Attributed Node Embeddingcited by 543
  8. 2020Principal Neighbourhood Aggregation for Graph Netscited by 477
  9. 2021Rethinking Graph Transformers with Spectral Attentioncited by 468
  10. 2019Provably Powerful Graph Networkscited by 385
  11. 2018Graph Convolutional Networks for Text Classificationcited by 345
  12. 2018Invariant and Equivariant Graph Networkscited by 339
  13. 2021Graph Neural Networks with Learnable Structural and Positional Representationscited by 326
  14. 2021Neural Bellman-Ford Networks: A General Graph Neural Network Framework for Link Predictioncited by 273
  15. 2022Long Range Graph Benchmarkcited by 258
  16. 2021Identity-aware Graph Neural Networkscited by 197
  17. 2021BernNet: Learning Arbitrary Graph Spectral Filters via Bernstein Approximationcited by 195
  18. 2022Representing Long-Range Context for Graph Neural Networks with Global Attentioncited by 193
  19. 2020The Surprising Power of Graph Neural Networks with Random Node Initializationcited by 190
  20. 2020Random Features Strengthen Graph Neural Networkscited by 184
  21. 2022Sign and Basis Invariant Networks for Spectral Graph Representation Learningcited by 176
  22. 2022How Powerful are Spectral Graph Neural Networkscited by 169
  23. 2023Exphormer: Sparse Transformers for Graphscited by 166
  24. 2021Equivariant Subgraph Aggregation Networkscited by 154
  25. 2021From Stars to Subgraphs: Uplifting Any GNN with Local Structure Awarenesscited by 154
  26. 2020Labeling Trick: A Theory of Using Graph Neural Networks for Multi-Node Representation Learningcited by 148
  27. 2021GraphiT: Encoding Graph Structure in Transformerscited by 146
  28. 2021Nested Graph Neural Networkscited by 136
  29. 2021DropGNN: Random Dropouts Increase the Expressiveness of Graph Neural Networkscited by 117
  30. 2022Understanding and Extending Subgraph GNNs by Rethinking Their Symmetriescited by 112
  31. 2020On Learning Sets of Symmetric Elementscited by 97
  32. 2022Equivariant and Stable Positional Encoding for More Powerful Graph Neural Networkscited by 94
  33. 2022Graph Neural Networks for Link Prediction with Subgraph Sketchingcited by 81
  34. 2020On the Universality of Rotation Equivariant Point Cloud Networkscited by 80
  35. 2022Neo-GNNs: Neighborhood Overlap-aware Graph Neural Networks for Link Predictioncited by 78
  36. 2020Subgraph Neural Networkscited by 73
  37. 2023Neural Common Neighbor with Completion for Link Predictioncited by 64
  38. 2023A Complete Expressiveness Hierarchy for Subgraph GNNs via Subgraph Weisfeiler-Lehman Testscited by 64

50 most cited of 59 All 59 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

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

2 papers.

  1. 2025On The Expressive Power of GNN Derivativescited by 0
  2. 2026Finite-Time Node Separation in Recurrent Graph Neural Networks with Persistent Gaussian Perturbationscited by 0