Skip to yearly menu bar Skip to main content

Workshop: Machine Learning for IoT: Datasets, Perception, and Understanding

Centaur: Federated Learning for Constrained Edge Devices

Fan Mo · Mohammad Malekzadeh · Soumyajit Chatterjee · Fahim Kawsar · Akhil Mathur


Federated learning (FL) 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% higher accuracy than local training on constrained devices with ~58% energy saving on average. Our experimental results also demonstrate the superior efficiency of Centaur when dealing with imbalanced data, client participation heterogeneity, and various network connection probabilities.

Chat is not available.