Secure Submodel Aggregation for Resource-Aware Federated Learning

Secure aggregation (SA) is a privacy-enhancing framework for federated learning, to aggregate the local gradient updates from the users without revealing them in the clear. Conventional SA frameworks are built under the assumption of homogeneous computational resources across the users, where users are bound to train a local model whose dimensions are as large as the global model, preventing resource-limited users from participating in training. In this work, we propose a novel secure submodel training framework to address this challenge, where users train and communicate partial submodels through an adaptable secure aggregation mechanism during training. Our framework enables the participation of all users with varying computation and communication resources, while ensuring formal information-theoretic privacy guarantees for the individual local updates.