mlsanityData to 7 Oct 2026

Gromov-Wasserstein Learning for Graph Matching and Node Embedding

arXiv 1901.06003 ↗First posted 17 Jan 2019cs.LG cs.SI stat.MLcited by 125

Not on the map. Why?

Abstract (arXiv)

A novel Gromov-Wasserstein learning framework is proposed to jointly match (align) graphs and learn embedding vectors for the associated graph nodes. Using Gromov-Wasserstein discrepancy, we measure the dissimilarity between two graphs and find their correspondence, according to the learned optimal transport. The node embeddings associated with the two graphs are learned under the guidance of the optimal transport, the distance of which not only reflects the topological structure of each graph but also yields the correspondence across the graphs. These two learning steps are mutually-beneficial, and are unified here by minimizing the Gromov-Wasserstein discrepancy with structural regularizers. This framework leads to an optimization problem that is solved by a proximal point method. We apply the proposed method to matching problems in real-world networks, and demonstrate its superior performance compared to alternative approaches.

Key facts. Cited by 125 papers in the map (data through 7 Oct 2026). First posted on arXiv 17 Jan 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 20; 2022: 25; 2023: 28; 2024: 13; 2025: 19; 2026: 20.

125 papers.

Sort:

By area:

  1. 2022PLOT: Prompt Learning with Optimal Transport for Vision-Language Modelscited by 64
  2. 2021Linear-Time Gromov Wasserstein Distances using Low Rank Couplings and Costscited by 61
  3. 2022Unbalanced Optimal Transport, from Theory to Numericscited by 45
  4. 2021Online Graph Dictionary Learningcited by 37
  5. 2024Temporally Consistent Unbalanced Optimal Transport for Unsupervised Action Segmentationcited by 37
  6. 2023OT-Attack: Enhancing Adversarial Transferability of Vision-Language Models via Optimal Transport Optimizationcited by 36
  7. 2021A Survey on Optimal Transport for Machine Learning: Theory and Applicationscited by 35
  8. 2022Graph Auto-Encoder Via Neighborhood Wasserstein Reconstructioncited by 28
  9. 2023Scalable Optimal Transport Methods in Machine Learning: A Contemporary Surveycited by 27
  10. 2022Wasserstein Task Embedding for Measuring Task Similaritiescited by 24
  11. 2023Hierarchical Multi-Marginal Optimal Transport for Network Alignmentcited by 24
  12. 2022Learning to Predict Graphs with Fused Gromov-Wasserstein Barycenterscited by 22
38 more
  1. 2021Semi-relaxed Gromov-Wasserstein divergence with applications on graphscited by 21
  2. 2022Fine-Tuning Graph Neural Networks via Graph Topology induced Optimal Transportcited by 19
  3. 2021Quantized Gromov-Wassersteincited by 18
  4. 2022Implicit Graphon Neural Representationcited by 18
  5. 2023ZegOT: Zero-shot Segmentation Through Optimal Transport of Text Promptscited by 16
  6. 2023A Fused Gromov-Wasserstein Framework for Unsupervised Knowledge Graph Entity Alignmentcited by 16
  7. 2021DIGRAC: Digraph Clustering Based on Flow Imbalancecited by 15
  8. 2023Robust Attributed Graph Alignment via Joint Structure Learning and Optimal Transportcited by 15
  9. 2023Graph Mixup with Soft Alignmentscited by 15
  10. 2023A Gromov--Wasserstein Geometric View of Spectrum-Preserving Graph Coarseningcited by 15
  11. 2023Fused Gromov-Wasserstein Graph Mixup for Graph-level Classificationscited by 15
  12. 2022Wasserstein Barycenter-based Model Fusion and Linear Mode Connectivity of Neural Networkscited by 14
  13. 2024Wasserstein Wormhole: Scalable Optimal Transport Distance with Transformerscited by 14
  14. 2025It's a (Blind) Match! Towards Vision-Language Correspondence without Parallel Datacited by 13
  15. 2022Efficient Approximation of Gromov-Wasserstein Distance Using Importance Sparsificationcited by 11
  16. 2025Joint Self-Supervised Video Alignment and Action Segmentationcited by 11
  17. 2021Reversible Gromov-Monge Sampler for Simulation-Based Inferencecited by 10
  18. 2023A Convergent Single-Loop Algorithm for Relaxation of Gromov-Wasserstein in Graph Datacited by 10
  19. 2023Semidefinite Relaxations of the Gromov-Wasserstein Distancecited by 10
  20. 2025Joint Optimal Transport and Embedding for Network Alignmentcited by 10
  21. 2022Hilbert Curve Projection Distance for Distribution Comparisoncited by 9
  22. 2022Auto-regressive Image Synthesis with Integrated Quantizationcited by 9
  23. 2023PEARL: Zero-shot Cross-task Preference Alignment and Robust Reward Learning for Robotic Manipulationcited by 9
  24. 2024OTSeg: Multi-prompt Sinkhorn Attention for Zero-Shot Semantic Segmentationcited by 9
  25. 2021FGOT: Graph Distances based on Filters and Optimal Transportcited by 7
  26. 2023Efficient Graph Field Integrators Meet Point Cloudscited by 7
  27. 2023Finding Heterophilic Neighbors via Confidence-based Subgraph Matching for Semi-supervised Node Classificationcited by 7
  28. 2023Globally solving the Gromov-Wasserstein problem for point clouds in low dimensional Euclidean spacescited by 7
  29. 2022Gromov-Wasserstein Discrepancy with Local Differential Privacy for Distributed Structural Graphscited by 6
  30. 2022Unbalanced CO-Optimal Transportcited by 6
  31. 2023Outlier-Robust Gromov-Wasserstein for Graph Datacited by 6
  32. 2023Bures-Wasserstein Means of Graphscited by 6
  33. 2024Double-Bounded Optimal Transport for Advanced Clustering and Classificationcited by 6
  34. 2021Sliced Multi-Marginal Optimal Transportcited by 5
  35. 2021COTReg:Coupled Optimal Transport based Point Cloud Registrationcited by 5
  36. 2022Multiscale Graph Comparison via the Embedded Laplacian Discrepancycited by 5
  37. 2022Unsupervised Manifold Alignment with Joint Multidimensional Scalingcited by 5
  38. 2022Conflict-Aware Pseudo Labeling via Optimal Transport for Entity Alignmentcited by 5

50 most cited of 125 All 125 (JSON)