Distributed learning of deep neural network over multiple agents

In domains such as health care and finance, shortage of labeled data and computational resources is a critical issue while developing machine learning algorithms. To address the issue of labeled data scarcity in training and deployment of neural network-based systems, we propose a new technique to t...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Journal of network and computer applications Jg. 116; S. 1 - 8
Hauptverfasser: Gupta, Otkrist, Raskar, Ramesh
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Elsevier Ltd 15.08.2018
Schlagworte:
Deep learning
Distributed systems
Multi party computation
Deep learning
Multi party computation
Distributed systems
ISSN:1084-8045, 1095-8592
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:In domains such as health care and finance, shortage of labeled data and computational resources is a critical issue while developing machine learning algorithms. To address the issue of labeled data scarcity in training and deployment of neural network-based systems, we propose a new technique to train deep neural networks over several data sources. Our method allows for deep neural networks to be trained using data from multiple entities in a distributed fashion. We evaluate our algorithm on existing datasets and show that it obtains performance which is similar to a regular neural network trained on a single machine. We further extend it to incorporate semi-supervised learning when training with few labeled samples, and analyze any security concerns that may arise. Our algorithm paves the way for distributed training of deep neural networks in data sensitive applications when raw data may not be shared directly.
ISSN:1084-8045
1095-8592
DOI:10.1016/j.jnca.2018.05.003