Distributed learning of deep neural network over multiple agents. (15th August 2018)

• Record Type: Journal Article
• Authors: Gupta, Otkrist; Raskar, Ramesh
• Is Part Of: Journal of network and computer applications. Volume 116(2018)
• Page Start: 1
• Page End: 8
• Publication Date: 2018-08-15
• Subjects: Multi party computation -- Deep learning -- Distributed systems; Microcomputers -- Periodicals; Computer networks -- Periodicals; Application software -- Periodicals; Micro-ordinateurs -- Périodiques; Réseaux d'ordinateurs -- Périodiques; Logiciels d'application -- Périodiques; Application software; Computer networks; Microcomputers; Periodicals; 004.05; 004
• DOI: 10.1016/j.jnca.2018.05.003
• Languages: English
• ISSNs: 1084-8045

Abstract

Abstract: 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.