Unsupervised Federated Optimization at the Edge: D2D-Enabled Learning without Labels

arXiv:2404.09861v1 Announce Type: new
Abstract: Federated learning (FL) is a popular solution for distributed machine learning (ML). While FL has traditionally been studied for supervised ML tasks, in many applications, it is impractical to assume availability of labeled data across devices. To this end, we develop Cooperative Federated unsupervised Contrastive Learning ({\tt CF-CL)} to facilitate FL across edge devices with unlabeled datasets. {\tt CF-CL} employs local device cooperation where either explicit (i.e., raw data) or implicit (i.e., embeddings) information is …

abstract applications arxiv availability cs.lg data devices distributed edge federated learning labels machine machine learning optimization popular solution tasks the edge type unsupervised