Learning the Structural Vocabulary of a Network

Navlakha, S. (February 2017) Learning the Structural Vocabulary of a Network. Neural Comput, 29 (2). pp. 287-312. ISSN 0899-7667

[thumbnail of Navlakha_2017_NeuralComp.pdf]
Preview
PDF
Navlakha_2017_NeuralComp.pdf - Published Version

Download (2MB) | Preview

Abstract

Networks have become instrumental in deciphering how information is processed and transferred within systems in almost every scientific field today. Nearly all network analyses, however, have relied on humans to devise structural features of networks believed to be most discriminative for an application. We present a framework for comparing and classifying networks without human-crafted features using deep learning. After training, autoencoders contain hidden units that encode a robust structural vocabulary for succinctly describing graphs. We use this feature vocabulary to tackle several network mining problems and find improved predictive performance versus many popular features used today. These problems include uncovering growth mechanisms driving the evolution of networks, predicting protein network fragility, and identifying environmental niches for metabolic networks. Deep learning offers a principled approach for mining complex networks and tackling graph-theoretic problems.

Item Type: Paper
Subjects: bioinformatics > computational biology > algorithms > machine learning
CSHL Authors:
Communities: CSHL labs > Navlakha lab
Depositing User: Matthew Dunn
Date: February 2017
Date Deposited: 06 Nov 2019 16:14
Last Modified: 06 Nov 2019 16:14
Related URLs:
URI: https://repository.cshl.edu/id/eprint/38627

Actions (login required)

Administrator's edit/view item Administrator's edit/view item