Ternary Compression for Communication-Efficient Federated Learning
arXiv:2003.03564 · doi:10.1109/TNNLS.2020.3041185
Abstract
Learning over massive data stored in different locations is essential in many real-world applications. However, sharing data is full of challenges due to the increasing demands of privacy and security with the growing use of smart mobile devices and IoT devices. Federated learning provides a potential solution to privacy-preserving and secure machine learning, by means of jointly training a global model without uploading data distributed on multiple devices to a central server. However, most existing work on federated learning adopts machine learning models with full-precision weights, and almost all these models contain a large number of redundant parameters that do not need to be transmitted to the server, consuming an excessive amount of communication costs. To address this issue, we propose a federated trained ternary quantization (FTTQ) algorithm, which optimizes the quantized networks on the clients through a self-learning quantization factor. Theoretical proofs of the convergence of quantization factors, unbiasedness of FTTQ, as well as a reduced weight divergence are given. On the basis of FTTQ, we propose a ternary federated averaging protocol (T-FedAvg) to reduce the upstream and downstream communication of federated learning systems. Empirical experiments are conducted to train widely used deep learning models on publicly available datasets, and our results demonstrate that the proposed T-FedAvg is effective in reducing communication costs and can even achieve slightly better performance on non-IID data in contrast to the canonical federated learning algorithms.
References in corpus (17)
- Distilling the Knowledge in a Neural Network
- Communication-Efficient Learning of Deep Networks from Decentralized Data
- Federated Learning: Challenges, Methods, and Future Directions
- Federated Learning with Non-IID Data
- DoReFa-Net: Training Low Bitwidth Convolutional Neural Networks with Low Bitwidth Gradients
- Federated Optimization: Distributed Machine Learning for On-Device Intelligence
- A Survey on Federated Learning Systems: Vision, Hype and Reality for Data Privacy and Protection
- Towards Federated Learning at Scale: System Design
- Ternary Weight Networks
- Trained Ternary Quantization
- TernGrad: Ternary Gradients to Reduce Communication in Distributed Deep Learning
- Communication-Efficient Federated Deep Learning with Asynchronous Model Update and Temporally Weighted Aggregation
- Federated Optimization:Distributed Optimization Beyond the Datacenter
- Sparse Communication for Distributed Gradient Descent
- Group Equivariant Convolutional Networks
- Model compression via distillation and quantization
- A Learning Framework for n-bit Quantized Neural Networks toward FPGAs