Embedding Alignment for Unsupervised Federated Learning via Smart Data Exchange
It addresses the challenge of applying federated learning to unlabeled data in distributed edge environments, which is incremental as it extends FL to unsupervised tasks with a novel data-sharing mechanism.
The paper tackles the problem of unsupervised federated learning with non-i.i.d. data across edge devices by proposing CF-CL, a method that uses smart data exchange via device cooperation, resulting in aligned latent spaces, faster global convergence, and effectiveness in extreme non-i.i.d. settings.
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.