Shift aggregate extract networks

12Citations
Citations of this article
13Readers
Mendeley users who have this article in their library.

Abstract

We introduce an architecture based on deep hierarchical decompositions to learn effective representations of large graphs. Our framework extends classic R-decompositions used in kernel methods, enabling nested part-of-part relations. Unlike recursive neural networks, which unroll a template on input graphs directly, we unroll a neural network template over the decomposition hierarchy, allowing us to deal with the high degree variability that typically characterize social network graphs. Deep hierarchical decompositions are also amenable to domain compression, a technique that reduces both space and time complexity by exploiting symmetries. We show empirically that our approach is able to outperform current state-of-the-art graph classification methods on large social network datasets, while at the same time being competitive on small chemobiological benchmark datasets.

Cite

CITATION STYLE

APA

Orsini, F., Baracchi, D., & Frasconi, P. (2018). Shift aggregate extract networks. Frontiers Robotics AI, 5(APR). https://doi.org/10.3389/frobt.2018.00042

Register to see more suggestions

Mendeley helps you to discover research relevant for your work.

Already have an account?

Save time finding and organizing research with Mendeley

Sign up for free