Optimal Transport for structured data with application on graphs

23 May 2018Titouan VayerLaetitia ChapelRémi FlamaryRomain TavenardNicolas Courty

This work considers the problem of computing distances between structured objects such as undirected graphs, seen as probability distributions in a specific metric space. We consider a new transportation distance (i.e. that minimizes a total cost of transporting probability masses) that unveils the geometric nature of the structured objects space... (read more)

PDF Abstract

Results from the Paper


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT LEADERBOARD
Graph Classification ENZYMES FGW sp Accuracy 71.00% # 2
Graph Classification MUTAG FGW wl h=4 sp Accuracy 88.42% # 22
Graph Classification MUTAG FGW wl h=2 sp Accuracy 86.42% # 33
Graph Classification MUTAG FGW raw sp Accuracy 83.26% # 43
Graph Classification NCI1 FGW wl h=4 sp Accuracy 86.42% # 2
Graph Classification NCI1 FGW wl h=2 sp Accuracy 85.82% # 4
Graph Classification NCI1 FGW raw sp Accuracy 72.82% # 33
Graph Classification PROTEINS FGW sp Accuracy 74.55% # 39