mlsanityData to 14 Oct 2026

Towards Pre-trained Graph Condensation via Optimal Transport

arXiv 2509.14722 ↗First posted 18 Sep 2025cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Graph condensation (GC) aims to distill the original graph into a small-scale graph, mitigating redundancy and accelerating GNN training. However, conventional GC approaches heavily rely on rigid GNNs and task-specific supervision. Such a dependency severely restricts their reusability and generalization across various tasks and architectures. In this work, we revisit the goal of ideal GC from the perspective of GNN optimization consistency, and then a generalized GC optimization objective is derived, by which those traditional GC methods can be viewed nicely as special cases of this optimization paradigm. Based on this, Pre-trained Graph Condensation (PreGC) via optimal transport is proposed to transcend the limitations of task- and architecture-dependent GC methods. Specifically, a hybrid-interval graph diffusion augmentation is presented to suppress the weak generalization ability of the condensed graph on particular architectures by enhancing the uncertainty of node states. Meanwhile, the matching between optimal graph transport plan and representation transport plan is tactfully established to maintain semantic consistencies across source graph and condensed graph spaces, thereby freeing graph condensation from task dependencies. To further facilitate the adaptation of condensed graphs to various downstream tasks, a traceable semantic harmonizer from source nodes to condensed nodes is proposed to bridge semantic associations through the optimized representation transport plan in pre-training. Extensive experiments verify the superiority and versatility of PreGC, demonstrating its task-independent nature and seamless compatibility with arbitrary GNNs.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 41 of its 63 references that are in the map. First posted on arXiv 18 Sep 2025.

Builds on

41 of 63 references.

References · 41

  1. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
  2. 2017Graph Attention Networkscited by 8,923
  3. 2017Inductive Representation Learning on Large Graphscited by 6,320
  4. 2019Simplifying Graph Convolutional Networkscited by 1,477
  5. 2018Predict then Propagate: Graph Neural Networks meet Personalized PageRankcited by 993
  6. 2018Weisfeiler and Leman Go Neural: Higher-order Graph Neural Networkscited by 881
  7. 2020Adaptive Universal Generalized PageRank Graph Neural Networkcited by 595
  8. 2020Dataset Condensation with Gradient Matchingcited by 516
  9. 2021BernNet: Learning Arbitrary Graph Spectral Filters via Bernstein Approximationcited by 195
  10. 2021Graph Condensation for Graph Neural Networkscited by 150
  11. 2023Improved Distribution Matching for Dataset Condensationcited by 124
  12. 2021A Unified Lottery Ticket Hypothesis for Graph Neural Networkscited by 118
29 more
  1. 2020Graph Optimal Transport for Cross-Domain Alignmentcited by 103
  2. 2022Condensing Graphs via One-Step Gradient Matchingcited by 100
  3. 2018Fused Gromov-Wasserstein distance for structured objects: theoretical foundations and mathematical propertiescited by 93
  4. 2022Graph Attention Multi-Layer Perceptroncited by 83
  5. 2023Structure-free Graph Condensation: From Large-scale Graphs to Condensed Graph-free Datacited by 71
  6. 2022Graph Condensation via Receptive Field Distribution Matchingcited by 60
  7. 2024A Comprehensive Survey on Graph Reduction: Sparsification, Coarsening, and Condensationcited by 57
  8. 2023CaT: Balanced Continual Graph Learning with Graph Condensationcited by 52
  9. 2023Does Graph Distillation See Like Vision Dataset Counterpart?cited by 45
  10. 2024Macro Graph Neural Networks for Online Billion-Scale Recommender Systemscited by 40
  11. 2021A Survey on Optimal Transport for Machine Learning: Theory and Applicationscited by 35
  12. 2023Graph Condensation for Inductive Node Representation Learningcited by 31
  13. 2024Navigating Complexity: Toward Lossless Graph Condensation via Expanding Window Matchingcited by 28
  14. 2024Rethinking and Accelerating Graph Condensation: A Training-Free Approach with Class Partitioncited by 23
  15. 2024Can Large Language Models Improve the Adversarial Robustness of Graph Neural Networks?cited by 23
  16. 2021Semi-relaxed Gromov-Wasserstein divergence with applications on graphscited by 21
  17. 2022Node-oriented Spectral Filtering for Graph Neural Networkscited by 17
  18. 2023Graph Distillation with Eigenbasis Matchingcited by 16
  19. 2023Mirage: Model-Agnostic Graph Distillation for Graph Classificationcited by 13
  20. 2023A Generalized Neural Diffusion Framework on Graphscited by 13
  21. 2024ARES: Alternating Reinforcement Learning and Supervised Fine-Tuning for Enhanced Multi-Modal Chain-of-Thought Reasoning Through Diverse AI Feedbackcited by 13
  22. 2024GC-Bench: An Open and Unified Benchmark for Graph Condensationcited by 12
  23. 2024A Topology-aware Graph Coarsening Framework for Continual Graph Learningcited by 11
  24. 2024Simple Graph Condensationcited by 8
  25. 2024Federated Graph Condensation with Information Bottleneck Principlescited by 8
  26. 2024AdaGMLP: AdaBoosting GNN-to-MLP Knowledge Distillationcited by 6
  27. 2024Contrastive Graph Condensation: Advancing Data Versatility through Self-Supervised Learningcited by 6
  28. 2025Rethinking Federated Graph Learning: A Data Condensation Perspectivecited by 6
  29. 2025Dynamic Graph Condensationcited by 1

Built on by

Not cited yet.