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

Paul KRZAKALA, Junjie Yang, Rémi Flamary, Florence d'Alché-Buc, Charlotte Laclau, Matthieu Labeau

Keywords: Optimal Transport, Graph Prediction, Structured Prediction, Graph, Deep Learning

TL;DR: We introduce Any2Graph a framework for deep end-to-end supervised graph prediction. The key components of the framework is PMFGW, an Optimal Transport Loss.

Abstract: 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).

Primary Area: Other (please use sparingly, only use the keyword field for more details)

Submission Number: 15793