LW-FedSSL: Resource-efficient Layer-wise Federated Self-supervised Learning

arXiv:2401.11647v2 Announce Type: replace
Abstract: Many studies integrate federated learning (FL) with self-supervised learning (SSL) to take advantage of raw training data distributed across edge devices. However, edge devices often struggle with high computation and communication costs imposed by SSL and FL algorithms. To tackle this hindrance, we propose LW-FedSSL, a layer-wise federated self-supervised learning approach that allows edge devices to incrementally train a single layer of the model at a time. Our LW-FedSSL comprises server-side calibration and representation alignment …

abstract algorithms arxiv communication computation costs cs.ai cs.lg data devices distributed edge edge devices federated learning however layer raw self-supervised learning ssl struggle studies supervised learning training training data type wise