HFL-Lite: Sparse Coding for Lightweight Hierarchical Federated Learning in Computation-Limited Sensor Networks
Tsinghua Science and Technology · 13.08.2026
DOI: 10.26599/tst.2026.9010080 ↗Kurz gefasst
Fachartikel in der Zeitschrift Tsinghua Science and Technology, online erschienen am 13.08.2026. Verfasst von Cangming Liang und 5 weiteren Autor:innen.
Abstract (Originalsprache)
The rapid growth of sensor-equipped edge devices calls for machine learning paradigms that are both lightweight and privacy-preserving. Federated learning (FL) enables distributed AI on edge data but still demands heavy forward and backward propagation on resource-constrained sensors. Split learning (SL) offloads computation to a server, yet its intermediate activations can leak private information. Homomorphic encryption closes this gap at the cost of prohibitive computation and bloated communication. We propose HFL-Lite, a hierarchical federated learning framework that achieves practical privacy without cryptographic primitives. Each sensor encodes its raw data into a compact sparse feature code via a lightweight sensor encoder. Only this code, which is insufficient to reconstruct the original data, leaves the device. An edge server synthesizes surrogate training samples from the uploaded codes, trains a teacher model, and distills knowledge back to the sensors. Because the sensors perform only one-way uploads, backward propagation, gradient transmission, and plaintext activation leakage are all eliminated. Experiments on the UCI HAR dataset show that HFL-Lite reduces per-round communication to 0.5 KB and sensor-side latency to 9 ms while delivering competitive accuracy.
Zitieren
APA
Liang, C., Li, K., Diao, Z., Meng, X., Liu, J., & Liang, W. (2026). HFL-Lite: Sparse Coding for Lightweight Hierarchical Federated Learning in Computation-Limited Sensor Networks. Tsinghua Science and Technology. https://doi.org/10.26599/tst.2026.9010080
Vancouver
Liang C, Li K, Diao Z, Meng X, Liu J, Liang W. HFL-Lite: Sparse Coding for Lightweight Hierarchical Federated Learning in Computation-Limited Sensor Networks. Tsinghua Science and Technology. 2026. doi:10.26599/tst.2026.9010080
BibTeX
@article{Liang2026,
author = {Liang, Cangming and Li, Kuan-Ching and Diao, Zulong and Meng, Xiangwei and Liu, Jie and Liang, Wei},
title = {HFL-Lite: Sparse Coding for Lightweight Hierarchical Federated Learning in Computation-Limited Sensor Networks},
journal = {Tsinghua Science and Technology},
year = {2026},
doi = {10.26599/tst.2026.9010080}
}
EUVIMED