000267851 001__ 267851
000267851 005__ 20190830103637.0
000267851 037__ $$aCONF
000267851 245__ $$aExtrapolating Paths with Graph Neural Networks
000267851 260__ $$bIJCAI, Inc.$$c2019-08-10
000267851 269__ $$a2019-08-10
000267851 336__ $$aConference Papers
000267851 520__ $$aWe consider the problem of path inference: given a path prefix, i.e., a partially observed sequence of nodes in a graph, we want to predict which nodes are in the missing suffix. In particular, we focus on natural paths occurring as a by-product of the interaction of an agent with a network—a driver on the transportation network, an information seeker in Wikipedia, or a client in an online shop. Our interest is sparked by the realization that, in contrast to shortest-path problems, natural paths are usually not optimal in any graph-theoretic sense, but might still follow predictable patterns. Our main contribution is a graph neural network called GRETEL. Conditioned on a path prefix, this network can efficiently extrapolate path suffixes, evaluate path likelihood, and sample from the future path distribution. Our experiments with GPS traces on a road network and user-navigation paths in Wikipedia confirm that GRETEL is able to adapt to graphs with very different properties, while also comparing favorably to previous solutions.
000267851 6531_ $$agraph neural networks
000267851 6531_ $$amachine learning
000267851 6531_ $$apaths
000267851 6531_ $$adata science
000267851 6531_ $$awikispeedia
000267851 6531_ $$aml-ai
000267851 700__ $$aCordonnier, Jean-Baptiste
000267851 700__ $$aLoukas, Andreas
000267851 7112_ $$aInternational Joint Conference on Artificial Intelligence$$cMacao, China$$dAugust 10-16, 2019
000267851 790__ $$w10.5281/zenodo.2597008$$2doi
000267851 8564_ $$s7959058$$uhttps://infoscience.epfl.ch/record/267851/files/Extrapolating%20Paths%20with%20Graph%20Neural%20Networks.pdf$$zFinal
000267851 8560_ $$fjean-baptiste.cordonnier@epfl.ch
000267851 909C0 $$pLTS2$$mpierre.vandergheynst@epfl.ch$$0252392$$zMarselli, Béatrice$$xU10380
000267851 909CO $$pconf$$pSTI$$ooai:infoscience.epfl.ch:267851
000267851 960__ $$aandreas.loukas@epfl.ch
000267851 961__ $$afantin.reichler@epfl.ch
000267851 973__ $$rREVIEWED$$aEPFL
000267851 981__ $$aoverwrite
000267851 980__ $$aCONF