Timezone: »

 
Spotlight
Learning to Predict Graphs with Fused Gromov-Wasserstein Barycenters
Luc Brogat-Motte · Rémi Flamary · Celine Brouard · Juho Rousu · Florence d'Alché-Buc

Wed Jul 20 02:45 PM -- 02:50 PM (PDT) @ Room 310
in Deep Learning/MISC »

This paper introduces a novel and generic framework to solve the flagship task of supervised labeled graph prediction by leveraging Optimal Transport tools. We formulate the problem as regression with the Fused Gromov-Wasserstein (FGW) loss and propose a predictive model relying on a FGW barycenter whose weights depend on inputs. First we introduce a non-parametric estimator based on kernel ridge regression for which theoretical results such as consistency and excess risk bound are proved. Next we propose an interpretable parametric model where the barycenter weights are modeled with a neural network and the graphs on which the FGW barycenter is calculated are additionally learned. Numerical experiments show the strength of the method and its ability to interpolate in the labeled graph space on simulated data and on a difficult metabolic identification problem where it can reach very good performance with very little engineering.

Keywords: APP: Chemistry and Drug Discovery · DL: Everything Else · MISC: Kernel methods · MISC: Supervised Learning

Author Information

Luc Brogat-Motte (Télécom Paris)
Rémi Flamary (École Polytechnique)
Celine Brouard (INRAE)
Juho Rousu (Aalto University)
Florence d'Alché-Buc (Télécom Paris, Institut Polytechnique de Paris)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors