Distributed learning of deep neural network over multiple agents

TL;DR

This paper introduces a distributed training method for deep neural networks that enables multiple data sources to collaboratively train models without sharing raw data, addressing data scarcity and privacy concerns.

Contribution

It presents a novel distributed training algorithm for deep neural networks that works with multiple data sources and incorporates semi-supervised learning, enhancing privacy and data efficiency.

Findings

Achieves performance comparable to centralized training.

Effectively incorporates semi-supervised learning with limited labeled data.

Addresses security concerns in distributed neural network training.

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.