mlsanityData to 7 Oct 2026

Enhancing Size Generalization in Graph Neural Networks through Disentangled Representation Learning

arXiv 2406.04601 ↗First posted 7 Jun 2024cs.LGcited by 6

Not on the map. Why?

Abstract (arXiv)

Although most graph neural networks (GNNs) can operate on graphs of any size, their classification performance often declines on graphs larger than those encountered during training. Existing methods insufficiently address the removal of size information from graph representations, resulting in sub-optimal performance and reliance on backbone models. In response, we propose DISGEN, a novel and model-agnostic framework designed to disentangle size factors from graph representations. DISGEN employs size- and task-invariant augmentations and introduces a decoupling loss that minimizes shared information in hidden representations, with theoretical guarantees for its effectiveness. Our empirical results show that DISGEN outperforms the state-of-the-art models by up to 6% on real-world datasets, underscoring its effectiveness in enhancing the size generalizability of GNNs. Our codes are available at: https://github.com/GraphmindDartmouth/DISGEN.

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Builds on 37 of its 55 references that are in the map. First posted on arXiv 7 Jun 2024.

Builds on

37 of 55 references.

References · 37

  1. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  2. 2018How Powerful are Graph Neural Networks?cited by 4,355
  3. 2019A Comprehensive Survey on Graph Neural Networkscited by 2,906
  4. 2020Open Graph Benchmark: Datasets for Machine Learning on Graphscited by 2,148
  5. 2019Invariant Risk Minimizationcited by 1,832
  6. 2020Graph Contrastive Learning with Augmentationscited by 1,203
  7. 2018Deep Graph Infomaxcited by 1,101
  8. 2017MoleculeNet: A Benchmark for Molecular Machine Learningcited by 1,037
  9. 2019GNNExplainer: Generating Explanations for Graph Neural Networkscited by 735
  10. 2020TUDataset: A collection of benchmark datasets for learning with graphscited by 718
  11. 2020GraphCodeBERT: Pre-training Code Representations with Data Flowcited by 600
  12. 2020Graph Contrastive Learning with Adaptive Augmentationcited by 519
25 more
  1. 2020Masked Label Prediction: Unified Message Passing Model for Semi-Supervised Classificationcited by 500
  2. 2020Parameterized Explainer for Graph Neural Networkcited by 423
  3. 2020Explainability in Graph Neural Networks: A Taxonomic Surveycited by 383
  4. 2018AllenNLP: A Deep Semantic Natural Language Processing Platformcited by 347
  5. 2018Invariant and Equivariant Graph Networkscited by 339
  6. 2021On Explainability of Graph Neural Networks via Subgraph Explorationscited by 280
  7. 2016Molecular Graph Convolutions: Moving Beyond Fingerprintscited by 238
  8. 2019Flexibly Fair Representation Learning by Disentanglementcited by 196
  9. 2021Training Graph Neural Networks with 1000 Layerscited by 169
  10. 2020Machine Learning on Graphs: A Model and Comprehensive Taxonomycited by 156
  11. 2019Relational Pooling for Graph Representationscited by 150
  12. 2022Learning Causally Invariant Representations for Out-of-Distribution Generalization on Graphscited by 144
  13. 2022Data Augmentation for Deep Graph Learning: A Surveycited by 132
  14. 2021Self-supervised Graph-level Representation Learning with Local and Global Structurecited by 125
  15. 2020From Local Structures to Size Generalization in Graph Neural Networkscited by 119
  16. 2021Size-Invariant Graph Representations for Graph Classification Extrapolationscited by 82
  17. 2020Fairness by Learning Orthogonal Disentangled Representationscited by 76
  18. 2020Convergence and Stability of Graph Convolutional Networks on Large Random Graphscited by 75
  19. 2021Multi-VAE: Learning Disentangled View-common and View-peculiar Visual Representations for Multi-view Clusteringcited by 51
  20. 2020Neural Execution Engines: Learning to Execute Subroutinescited by 36
  21. 2022SizeShiftReg: a Regularization Method for Improving Size-Generalization in Graph Neural Networkscited by 36
  22. 2021Augmentations in Graph Contrastive Learning: Current Methodological Flaws & Towards Better Practicescited by 24
  23. 2021Semi-supervised Domain Adaptation via Sample-to-Sample Self-Distillationcited by 23
  24. 2023ENGAGE: Explanation Guided Data Augmentation for Graph Representation Learningcited by 5
  25. 2019Graph Neural Networks for Small Graph and Giant Network Representation Learning: An Overviewcited by 3

Built on by

Cited by year

Citing papers per year: 2024: 4; 2025: 2.

6 papers.

  1. 2024A Survey of Deep Graph Learning under Distribution Shifts: from Graph Out-of-Distribution Generalization to Adaptationcited by 16
  2. 2024Graph Neural Network Generalization with Gaussian Mixture Model Based Augmentationcited by 2
  3. 2024Exploring Consistency in Graph Representations:from Graph Kernels to Graph Neural Networkscited by 1
  4. 2025From Small to Large: Generalization Bounds for Transformers on Variable-Size Inputscited by 1
  5. 2024Score-based Conditional Out-of-Distribution Augmentation for Graph Covariate Shiftcited by 0
  6. 2025Learning Repetition-Invariant Representations for Polymer Informaticscited by 0