Ngu Nguyen presented our paper at Workshop on Hot Topics in Social and Mobile Connected Smart Objects. The workshop focuses on experiences with the design, implementation, deployment, operation, and evaluation of novel systems for smart objects and the social aspects of these systems in the emerging cooperative environments.

Abstract

Machine learning models can deal with data samples scattered among distributed agents, each of which holds a non-overlapping set of sample features. In this paper, we propose a training algorithm that does not require communication between these agents. A coordinator can access ground-truth labels and produces binary feedback to guide the optimization process towards optimal model parameters. We mimic the gradient descent technique with information observed locally at each agent. We experimented with the logistic regression model on multiple benchmark datasets and achieves promising results in terms of convergence rate and communication load.