Smart Information Exchange for Unsupervised Federated Learning via Reinforcement Learning
This work addresses data heterogeneity in decentralized machine learning for applications like edge computing, but it is incremental as it builds on existing FL and D2D transfer concepts.
The paper tackles the challenge of non-i.i.d. data in unsupervised federated learning by proposing a reinforcement learning method to optimize device-to-device data transfer graphs, resulting in improved convergence speed and straggler resilience as shown in numerical analyses.
One of the main challenges of decentralized machine learning paradigms such as Federated Learning (FL) is the presence of local non-i.i.d. datasets. Device-to-device transfers (D2D) between distributed devices has been shown to be an effective tool for dealing with this problem and robust to stragglers. In an unsupervised case, however, it is not obvious how data exchanges should take place due to the absence of labels. In this paper, we propose an approach to create an optimal graph for data transfer using Reinforcement Learning. The goal is to form links that will provide the most benefit considering the environment's constraints and improve convergence speed in an unsupervised FL environment. Numerical analysis shows the advantages in terms of convergence speed and straggler resilience of the proposed method to different available FL schemes and benchmark datasets.