Embedding Alignment for Unsupervised Federated Learning via Smart Data Exchange

TL;DR

This paper introduces CF-CL, a novel unsupervised federated learning method that uses smart device-to-device data exchange to improve model alignment, convergence speed, and performance in non-i.i.d. data environments.

Contribution

The paper proposes a new cooperative federated unsupervised contrastive learning approach with a smart data sharing mechanism for better model alignment and efficiency.

Findings

CF-CL achieves alignment of latent spaces across devices

It results in faster convergence with fewer global aggregations

Effective in extreme non-i.i.d. data scenarios

Abstract

Federated learning (FL) has been recognized as one of the most promising solutions for distributed machine learning (ML). In most of the current literature, FL has been studied for supervised ML tasks, in which edge devices collect labeled data. Nevertheless, in many applications, it is impractical to assume existence of labeled data across devices. To this end, we develop a novel methodology, Cooperative Federated unsupervised Contrastive Learning (CF-CL), for FL across edge devices with unlabeled datasets. CF-CL employs local device cooperation where data are exchanged among devices through device-to-device (D2D) communications to avoid local model bias resulting from non-independent and identically distributed (non-i.i.d.) local datasets. CF-CL introduces a push-pull smart data sharing mechanism tailored to unsupervised FL settings, in which, each device pushes a subset of its local datapoints to its neighbors as reserved data points, and pulls a set of datapoints from its neighbors, sampled through a probabilistic importance sampling technique. We demonstrate that CF-CL leads to (i) alignment of unsupervised learned latent spaces across devices, (ii) faster global convergence, allowing for less frequent global model aggregations; and (iii) is effective in extreme non-i.i.d. data settings across the devices.