mlsanityData to 14 Oct 2026

Any2Graph: Deep End-To-End Supervised Graph Prediction With An Optimal Transport Loss

arXiv 2402.12269 ↗First posted 19 Feb 2024cs.LGcited by 7

Not on the map. Why?

Abstract (arXiv)

We propose Any2graph, a generic framework for end-to-end Supervised Graph Prediction (SGP) i.e. a deep learning model that predicts an entire graph for any kind of input. The framework is built on a novel Optimal Transport loss, the Partially-Masked Fused Gromov-Wasserstein, that exhibits all necessary properties (permutation invariance, differentiability and scalability) and is designed to handle any-sized graphs. Numerical experiments showcase the versatility of the approach that outperform existing competitors on a novel challenging synthetic dataset and a variety of real-world tasks such as map construction from satellite image (Sat2Graph) or molecule prediction from fingerprint (Fingerprint2Graph).

Key facts. Cited by 7 papers in the map (data through 14 Oct 2026). Builds on 30 of its 56 references that are in the map. First posted on arXiv 19 Feb 2024.

Builds on

30 of 56 references.

References · 30

  1. 2017Attention Is All You Needcited by 60,361
  2. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  3. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  4. 2020End-to-End Object Detection with Transformerscited by 7,414
  5. 2018How Powerful are Graph Neural Networks?cited by 4,393
  6. 2017Deep Setscited by 1,421
  7. 2017MoleculeNet: A Benchmark for Molecular Machine Learningcited by 1,051
  8. 2020On Layer Normalization in the Transformer Architecturecited by 922
  9. 2019Diffusion Improves Graph Learningcited by 414
  10. 2018MolGAN: An implicit generative model for small molecular graphscited by 393
  11. 2018GraphVAE: Towards Generation of Small Graphs Using Variational Autoencoderscited by 383
  12. 2016Deep Biaffine Attention for Neural Dependency Parsingcited by 334
18 more
  1. 2018Optimal Transport for structured data with application on graphscited by 172
  2. 2021A Comprehensive Survey of Scene Graphs: Generation and Applicationcited by 125
  3. 2022Panoptic Scene Graph Generationcited by 114
  4. 2021Energy-Based Learning for Scene Graph Generationcited by 104
  5. 2018Fused Gromov-Wasserstein distance for structured objects: theoretical foundations and mathematical propertiescited by 93
  6. 2022Relationformer: A Unified Framework for Image-to-Graph Generationcited by 67
  7. 2021Linear-Time Gromov Wasserstein Distances using Low Rank Couplings and Costscited by 61
  8. 2020The Unbalanced Gromov Wasserstein Distance: Conic Formulation and Relaxationcited by 56
  9. 2015Randomized sketches for kernels: Fast and optimal non-parametric regressioncited by 31
  10. 2019A Two-Step Graph Convolutional Decoder for Molecule Generationcited by 25
  11. 2022Aligning individual brains with Fused Unbalanced Gromov-Wassersteincited by 23
  12. 2022Learning to Predict Graphs with Fused Gromov-Wasserstein Barycenterscited by 22
  13. 2019Image-Conditioned Graph Generation for Road Network Extractioncited by 17
  14. 2021Non-Autoregressive Semantic Parsing for Compositional Task-Oriented Dialogcited by 17
  15. 2022Knowledge Graph Generation From Textcited by 15
  16. 2023Unbalanced Optimal Transport: A Unified Framework for Object Detectioncited by 15
  17. 2022Fast Kernel Methods for Generic Lipschitz Losses via p-Sparsified Sketchescited by 5
  18. 2014Graph matching: relax or not?cited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 2; 2026: 5.

7 papers.

  1. 2025The quest for the GRAph Level autoEncoder (GRALE)cited by 8
  2. 2026Conformal Graph Prediction with Z-Gromov-Wasserstein Distancescited by 2
  3. 2026GraViti: Graph-Level Variational Autoencoders with Relaxed Permutation Invariancecited by 2
  4. 2025Synthetic Data for Blood Vessel Network Extractioncited by 1
  5. 2026Building Deep Graph Predictors with Graph Imitation Learningcited by 0
  6. 2026LineGraph2Road: Structural Graph Reasoning on Line Graphs for Road Network Extractioncited by 0
  7. 2026Graph Matching Relaxations and Amortization for Supervised Graph Predictioncited by 0