Collective Learning
This addresses the challenge of enabling heterogeneous systems with varying computational capabilities to collaborate effectively in distributed learning, though it appears incremental as it builds on existing semi-supervised and consensus methods.
The paper tackles the problem of distributed semi-supervised learning by proposing collective learning, a framework where agents alternate between self-training on local labeled data and collective training using consensus-based proxy-labels on shared unlabeled data, resulting in higher performance for cooperating agents compared to individual learning as shown in image classification experiments.
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.