@article{yue_jin_wong_dai_2022, title={Communication-Efficient Federated Learning via Predictive Coding}, volume={16}, ISSN={["1941-0484"]}, DOI={10.1109/JSTSP.2022.3142678}, abstractNote={Federated learning can enable remote workers to collaboratively train a shared machine learning model while allowing training data to be kept locally. In the use case of wireless mobile devices, the communication overhead is a critical bottleneck due to limited power and bandwidth. Prior work has utilized various data compression tools such as quantization and sparsification to reduce the overhead. In this paper, we propose a predictive coding based compression scheme for federated learning. The scheme has shared prediction functions among all devices and allows each worker to transmit a compressed residual vector derived from the reference. In each communication round, we select the predictor and quantizer based on the rate–distortion cost, and further reduce the redundancy with entropy coding. Extensive simulations reveal that the communication cost can be reduced up to 99% with even better learning performance when compared with other baseline methods.}, number={3}, journal={IEEE JOURNAL OF SELECTED TOPICS IN SIGNAL PROCESSING}, author={Yue, Kai and Jin, Richeng and Wong, Chau-Wai and Dai, Huaiyu}, year={2022}, month={Apr}, pages={369–380} }
 @article{yue_jin_wong_dai_2022, title={Federated Learning via Plurality Vote}, volume={12}, ISSN={["2162-2388"]}, DOI={10.1109/TNNLS.2022.3225715}, abstractNote={Federated learning allows collaborative clients to solve a machine-learning problem while preserving data privacy. Recent studies have tackled various challenges in federated learning, but the joint optimization of communication overhead, learning reliability, and deployment efficiency is still an open problem. To this end, we propose a new scheme named federated learning via plurality vote (FedVote). In each communication round of FedVote, clients transmit binary or ternary weights to the server with low communication overhead. The model parameters are aggregated via weighted voting to enhance the resilience against Byzantine attacks. When deployed for inference, the model with binary or ternary weights is resource-friendly to edge devices. Our results demonstrate that the proposed method can reduce quantization error and converges faster compared to the methods directly quantizing the model updates.}, journal={IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS}, author={Yue, Kai and Jin, Richeng and Wong, Chau-Wai and Dai, Huaiyu}, year={2022}, month={Dec} }