Collective Learning

TL;DR

This paper introduces collective learning, a framework inspired by human collaboration, enabling distributed systems with different resources to improve image classification performance through cooperation and consensus-based label sharing.

Contribution

It presents a novel collective learning framework combining self-training and consensus-based label sharing for heterogeneous distributed systems.

Findings

Enhanced classification accuracy through cooperation

Effective label sharing in heterogeneous networks

Performance improvements over isolated learning

Abstract

In this paper, we introduce the concept of collective learning (CL) which exploits the notion of collective intelligence in the field of distributed semi-supervised learning. The proposed framework draws inspiration from the learning behavior of human beings, who alternate phases involving collaboration, confrontation and exchange of views with other consisting of studying and learning on their own. On this regard, CL comprises two main phases: a self-training phase in which learning is performed on local private (labeled) data only and a collective training phase in which proxy-labels are assigned to shared (unlabeled) data by means of a consensus-based algorithm. In the considered framework, heterogeneous systems can be connected over the same network, each with different computational capabilities and resources and everyone in the network may take advantage of the cooperation and will eventually reach higher performance with respect to those it can reach on its own. An extensive experimental campaign on an image classification problem emphasizes the properties of CL by analyzing the performance achieved by the cooperating agents.