FedADAS: Communication-Efficient Federated Distillation for On-Device Driver Yawn Recognition in Vehicular Networks

TL;DR

FedADAS is a novel federated distillation framework that enables communication-efficient, personalized driver yawn recognition models on heterogeneous edge devices in vehicular networks.

Contribution

It introduces a method for collaborative on-device learning with model heterogeneity and reduced communication overhead using soft logits exchange.

Findings

Achieves up to 9974x reduction in communication cost.

Provides robust yawn recognition with high accuracy on edge devices.

Outperforms traditional federated learning in heterogeneous, high-participation scenarios.

Abstract

Driver fatigue is a critical safety concern in advanced driver assistance systems. Driver monitoring models trained off-site on static datasets adapt poorly to real-world conditions, while standard federated learning imposes high communication overhead, assumes homogeneous architectures, and struggles with personalized driver data. We present FedADAS, a federated distillation framework enabling collaborative on-device learning across heterogeneous vehicular networks. FedADAS enables full model heterogeneity by exchanging only soft logits on a shared public dataset, allowing each vehicle to run a customized model tailored to its computational constraints. Additionally, we introduce a yawn recognition pipeline supporting training and inference on edge devices that provides two robust architectures: Performance-Efficient (99.7 MB) achieving 98.3% F1-score with 1.99ms inference time on a Jetson NANO, and a Memory-Efficient (0.6 MB) that trains an epoch in 6.12 minutes on a Jetson AGX Orin. In experiments with up to 115 edge clients, FedADAS significantly outperforms traditional federated learning approaches at higher client participation, achieving up to 9974x reduction in communication cost while maintaining a superior tradeoff between personalization and generalization under extreme data heterogeneity, demonstrating its suitability for real-world deployment. Code is available at https://opensource.silicon-austria.com/mujtabaa/fedadas