Resource-Constrained Federated Learning with Heterogeneous Labels and Models

TL;DR

This paper introduces a federated learning framework that effectively handles label heterogeneity and model differences in resource-constrained IoT environments, demonstrating significant accuracy improvements and on-device feasibility.

Contribution

The paper proposes a novel $oldsymbol{ extalpha}$-weighted federated aggregation method to address label heterogeneity and demonstrates its effectiveness on IoT devices.

Findings

Achieved at least 16.7% accuracy increase on Animals-10 dataset.

Validated on Raspberry Pi 2 for on-device federated learning.

Effectively handles label and model heterogeneity in resource-limited settings.

Abstract

Various IoT applications demand resource-constrained machine learning mechanisms for different applications such as pervasive healthcare, activity monitoring, speech recognition, real-time computer vision, etc. This necessitates us to leverage information from multiple devices with few communication overheads. Federated Learning proves to be an extremely viable option for distributed and collaborative machine learning. Particularly, on-device federated learning is an active area of research, however, there are a variety of challenges in addressing statistical (non-IID data) and model heterogeneities. In addition, in this paper we explore a new challenge of interest -- to handle label heterogeneities in federated learning. To this end, we propose a framework with simple $\alpha$-weighted federated aggregation of scores which leverages overlapping information gain across labels, while saving bandwidth costs in the process. Empirical evaluation on Animals-10 dataset (with 4 labels for effective elucidation of results) indicates an average deterministic accuracy increase of at least ~16.7%. We also demonstrate the on-device capabilities of our proposed framework by experimenting with federated learning and inference across different iterations on a Raspberry Pi 2, a single-board computing platform.