mlsanityData to 7 Oct 2026

Improving Expressivity of GNNs with Subgraph-specific Factor Embedded Normalization

arXiv 2305.19903 ↗First posted 31 May 2023cs.LG cs.AIcited by 12

Not on the map. Why?

Abstract (arXiv)

Graph Neural Networks (GNNs) have emerged as a powerful category of learning architecture for handling graph-structured data. However, existing GNNs typically ignore crucial structural characteristics in node-induced subgraphs, which thus limits their expressiveness for various downstream tasks. In this paper, we strive to strengthen the representative capabilities of GNNs by devising a dedicated plug-and-play normalization scheme, termed as SUbgraph-sPEcific FactoR Embedded Normalization (SuperNorm), that explicitly considers the intra-connection information within each node-induced subgraph. To this end, we embed the subgraph-specific factor at the beginning and the end of the standard BatchNorm, as well as incorporate graph instance-specific statistics for improved distinguishable capabilities. In the meantime, we provide theoretical analysis to support that, with the elaborated SuperNorm, an arbitrary GNN is at least as powerful as the 1-WL test in distinguishing non-isomorphism graphs. Furthermore, the proposed SuperNorm scheme is also demonstrated to alleviate the over-smoothing phenomenon. Experimental results related to predictions of graph, node, and link properties on the eight popular datasets demonstrate the effectiveness of the proposed method. The code is available at https://github.com/chenchkx/SuperNorm.

Key facts. Cited by 12 papers in the map (data through 7 Oct 2026). Builds on 52 of its 75 references that are in the map. First posted on arXiv 31 May 2023.

Builds on

52 of 75 references.

References · 52

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  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. 2018How Powerful are Graph Neural Networks?cited by 4,355
  7. 2020Open Graph Benchmark: Datasets for Machine Learning on Graphscited by 2,148
  8. 2018Deeper Insights into Graph Convolutional Networks for Semi-Supervised Learningcited by 1,099
  9. 2018Representation Learning on Graphs with Jumping Knowledge Networkscited by 875
  10. 2020Simple and Deep Graph Convolutional Networkscited by 857
  11. 2020TUDataset: A collection of benchmark datasets for learning with graphscited by 718
  12. 2019DropEdge: Towards Deep Graph Convolutional Networks on Node Classificationcited by 679
38 more
  1. 2020Benchmarking Graph Neural Networkscited by 672
  2. 2020Contrastive Multi-View Representation Learning on Graphscited by 651
  3. 2023LLM-Pruner: On the Structural Pruning of Large Language Modelscited by 643
  4. 2019DeepGCNs: Can GCNs Go as Deep as CNNs?cited by 527
  5. 2019InfoGraph: Unsupervised and Semi-supervised Graph-Level Representation Learning via Mutual Information Maximizationcited by 441
  6. 2021Graph Neural Networks with Learnable Structural and Positional Representationscited by 326
  7. 2020Improving Graph Neural Network Expressivity via Subgraph Isomorphism Countingcited by 312
  8. 2019PairNorm: Tackling Oversmoothing in GNNscited by 297
  9. 2020Towards Deeper Graph Neural Networkscited by 296
  10. 2020SIGN: Scalable Inception Graph Neural Networkscited by 283
  11. 2021Combinatorial optimization and reasoning with graph neural networkscited by 267
  12. 2020Spatial-Temporal Fusion Graph Neural Networks for Traffic Flow Forecastingcited by 212
  13. 2022G-Mixup: Graph Data Augmentation for Graph Classificationcited by 145
  14. 2023Dataset Distillation: A Comprehensive Reviewcited by 126
  15. 2020GraphNorm: A Principled Approach to Accelerating Graph Neural Network Trainingcited by 116
  16. 2022Dataset Distillation via Factorizationcited by 115
  17. 2020Towards Deeper Graph Neural Networks with Differentiable Group Normalizationcited by 113
  18. 2021Combinatorial Optimization with Physics-Inspired Graph Neural Networkscited by 107
  19. 2023LRRNet: A Novel Representation Learning Guided Fusion Network for Infrared and Visible Imagescited by 87
  20. 2020Large-scale Robust Deep AUC Maximization: A New Surrogate Loss and Empirical Studies on Medical Image Classificationcited by 84
  21. 2022Deep Model Reassemblycited by 78
  22. 2021DIG: A Turnkey Library for Diving into Graph Deep Learning Researchcited by 76
  23. 2020Tackling Over-Smoothing for General Graph Convolutional Networkscited by 66
  24. 2022Factorizing Knowledge in Neural Networkscited by 59
  25. 2020Revisiting Over-smoothing in Deep GCNscited by 55
  26. 2020Understanding and Resolving Performance Degradation in Graph Convolutional Networkscited by 53
  27. 2022Root-aligned SMILES: A Tight Representation for Chemical Reaction Predictioncited by 49
  28. 2021Bag of Tricks for Training Deeper Graph Neural Networks: A Comprehensive Benchmark Studycited by 36
  29. 2021Pooling Architecture Search for Graph Classificationcited by 36
  30. 2022Learning Graph Neural Networks for Image Style Transfercited by 29
  31. 2021Meta-Aggregator: Learning to Aggregate for 1-bit Graph Neural Networkscited by 24
  32. 2022Riemannian Local Mechanism for SPD Neural Networkscited by 22
  33. 2023Deep Graph Reprogrammingcited by 22
  34. 2021Distribution Knowledge Embedding for Graph Poolingcited by 19
  35. 2020Learning Graph Normalization for Graph Neural Networkscited by 16
  36. 2023Segment Anything in Non-Euclidean Domains: Challenges and Opportunitiescited by 16
  37. 2021Joint Detection and Localization of Stealth False Data Injection Attacks in Smart Grids using Graph Neural Networkscited by 15
  38. 2022Label-Enhanced Graph Neural Network for Semi-supervised Node Classificationcited by 11

50 most cited of 52 All 52 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 1; 2024: 8; 2025: 2; 2026: 1.

12 papers.

  1. 2024FreeCustom: Tuning-Free Customized Image Generation for Multi-Concept Compositioncited by 49
  2. 2024Understanding Oversmoothing in Diffusion-Based GNNs From the Perspective of Operator Semigroup Theorycited by 8
  3. 2024A Lie Group Approach to Riemannian Batch Normalizationcited by 8
  4. 2024Unveiling Global Interactive Patterns across Graphs: Towards Interpretable Graph Neural Networkscited by 8
  5. 2024GRANOLA: Adaptive Normalization for Graph Neural Networkscited by 7
  6. 2024Powerformer: A Section-adaptive Transformer for Power Flow Adjustmentcited by 5
  7. 2024Foundations and Frontiers of Graph Learning Theorycited by 3
  8. 2025DreamAudio: Customized Text-to-Audio Generation with Diffusion Modelscited by 2
  9. 2023Message-passing selection: Towards interpretable GNNs for graph classificationcited by 1
  10. 2025Studying and Improving Graph Neural Network-based Motif Estimationcited by 1
  11. 2024Learning a Mini-batch Graph Transformer via Two-stage Interaction Augmentationcited by 0
  12. 2026LEED: Local Embedding Evolution Distance for over-smoothing estimation and virtual node selection in GNNcited by 0