Shift Aggregate Extract Networks

Francesco Orsini, Daniele Baracchi, Paolo Frasconi

Nov 04, 2016 (modified: Dec 28, 2016) ICLR 2017 conference submission readers: everyone
  • Abstract: The Shift Aggregate Extract Network SAEN is an architecture for learning representations on social network data. SAEN decomposes input graphs into hierarchies made of multiple strata of objects. Vector representations of each object are learnt by applying 'shift', 'aggregate' and 'extract' operations on the vector representations of its parts. We propose an algorithm for domain compression which takes advantage of symmetries in hierarchical decompositions to reduce the memory usage and obtain significant speedups. Our method is empirically evaluated on real world social network datasets, outperforming the current state of the art.
  • TL;DR: Shift Aggregate Extract Networks for learning on social network data
  • Keywords: Supervised Learning
  • Conflicts:,