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).
@article{arxiv.2402.12269,
title = {Any2Graph: Deep End-To-End Supervised Graph Prediction With An Optimal Transport Loss},
author = {Paul Krzakala and Junjie Yang and Rémi Flamary and Florence d'Alché-Buc and Charlotte Laclau and Matthieu Labeau},
journal= {arXiv preprint arXiv:2402.12269},
year = {2024}
}