On-device machine learning (ML) enables the training process to exploit a massive amount of user-generated private data samples. To enjoy this benefit, inter-device communication overhead should be minimized. With this end, we propose federated distillation (FD), a distributed model training algorithm whose communication payload size is much smaller than a benchmark scheme, federated learning (FL), particularly when the model size is large. Moreover, user-generated data samples are likely to become non-IID across devices, which commonly degrades the performance compared to the case with an IID dataset. To cope with this, we propose federated augmentation (FAug), where each device collectively trains a generative model, and thereby augments its local data towards yielding an IID dataset. Empirical studies demonstrate that FD with FAug yields around 26x less communication overhead while achieving 95-98% test accuracy compared to FL.
@article{arxiv.1811.11479,
title = {Communication-Efficient On-Device Machine Learning: Federated Distillation and Augmentation under Non-IID Private Data},
author = {Eunjeong Jeong and Seungeun Oh and Hyesung Kim and Jihong Park and Mehdi Bennis and Seong-Lyun Kim},
journal= {arXiv preprint arXiv:1811.11479},
year = {2023}
}
Comments
presented at the 32nd Conference on Neural Information Processing Systems (NIPS 2018), 2nd Workshop on Machine Learning on the Phone and other Consumer Devices (MLPCD 2), Montr\'eal, Canada