Communication Dans Un Congrès Année : 2024

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

Résumé

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).

Fichier principal
Vignette du fichier
NeurIPS-2024-any2graph-deep-end-to-end-supervised-graph-prediction-with-an-optimal-transport-loss-Paper-Conference.pdf (1.33 Mo) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)
Licence

Dates et versions

hal-05010720 , version 1 (28-03-2025)

Licence

Identifiants

Citer

Paul Krzakala, Junjie Yang, Rémi Flamary, Florence d'Alché-Buc, Charlotte Laclau, et al.. Any2Graph: Deep End-To-End Supervised Graph Prediction With An Optimal Transport Loss. 38th Annual Conference on Neural Information Processing Systems (NeurIPS 2024), Dec 2024, Vancouver, Canada. ⟨10.48550/arXiv.2402.12269⟩. ⟨hal-05010720⟩
348 Consultations
321 Téléchargements

Altmetric

Partager

  • More