Centaur: Federated Learning for Constrained Edge Devices

11/08/2022
by   Fan Mo, et al.
0

Federated learning (FL) on deep neural networks facilitates new applications at the edge, especially for wearable and Internet-of-Thing devices. Such devices capture a large and diverse amount of data, but they have memory, compute, power, and connectivity constraints which hinder their participation in FL. We propose Centaur, a multitier FL framework, enabling ultra-constrained devices to efficiently participate in FL on large neural nets. Centaur combines two major ideas: (i) a data selection scheme to choose a portion of samples that accelerates the learning, and (ii) a partition-based training algorithm that integrates both constrained and powerful devices owned by the same user. Evaluations, on four benchmark neural nets and three datasets, show that Centaur gains  10 with  58 the superior efficiency of Centaur when dealing with imbalanced data, client participation heterogeneity, and various network connection probabilities.

READ FULL TEXT

Please sign up or login with your details

Forgot password? Click here to reset