Combined Learning of Neural Network Weights for Privacy in Collaborative Tasks

04/30/2022
by   Aline R. Ioste, et al.
0

We introduce CoLN, Combined Learning of Neural network weights, a novel method to securely combine Machine Learning models over sensitive data with no sharing of data. With CoLN, local hosts use the same Neural Network architecture and base parameters to train a model using only locally available data. Locally trained models are then submitted to a combining agent, which produces a combined model. The new model's parameters can be sent back to hosts, and can then be used as initial parameters for a new training iteration. CoLN is capable of combining several distributed neural networks of the same kind but is not restricted to any single neural architecture. In this paper we detail the combination algorithm and present experiments with feed-forward, convolutional, and recurrent Neural Network architectures, showing that the CoLN combined model approximates the performance of a hypothetical ideal centralized model, trained using the combination of the local datasets. CoLN can contribute to secure collaborative research, as required in the medical area, where privacy issues preclude data sharing, but where the limitations of local data demand information derived from larger datasets.

READ FULL TEXT
research
09/04/2019

Big Data Intelligence Using Distributed Deep Neural Networks

Large amount of data is often required to train and deploy useful machin...
research
06/21/2019

Privacy Preserving QoE Modeling using Collaborative Learning

Machine Learning based Quality of Experience (QoE) models potentially su...
research
07/16/2021

Federated Whole Prostate Segmentation in MRI with Personalized Neural Architectures

Building robust deep learning-based models requires diverse training dat...
research
06/18/2019

Secure Architectures Implementing Trusted Coalitions for Blockchained Distributed Learning (TCLearn)

Distributed learning across a coalition of organizations allows the memb...
research
09/17/2021

DiNNO: Distributed Neural Network Optimization for Multi-Robot Collaborative Learning

We present a distributed algorithm that enables a group of robots to col...
research
02/10/2017

Local System Voting Feature for Machine Translation System Combination

In this paper, we enhance the traditional confusion network system combi...
research
03/01/2022

Tricks and Plugins to GBM on Images and Sequences

Convolutional neural networks (CNNs) and transformers, which are compose...

Please sign up or login with your details

Forgot password? Click here to reset