IEEE Transactions on Network Science and Engineering · 2022 · 99 citations · 35 references
ComputingComputer ScienceComputer SystemsDistributed SystemsMachine LearningPrivacy EngineeringData PrivacyFederated LearningFederated Learning PrivacyMachine Learning For Big DataPrivacy-preserving ProtocolsSecure Multi-party ComputationBlockchain-based Data SharingBlockchain-based SecurityFederated Training ArchitectureModel CompressionPrivacy LeakagePrivacy-preserving LearningPrivacy-preserving Machine LearningPrivacy-preserving Model Updates
Conventional machine learning approaches aggregate all training data in a central server, which causes massive communication overhead of data transmission and is also vulnerable to privacy leakage. Thereby, blockchain-based federated learning has emerged to protect Artificial Intelligence of Things (AIoT) devices from exposing their private data by the Federated Learning (FL) framework, and also enables decentralized model training without the vulnerability of a central server. However, the existing blockchain-based FL systems still suffer from (i) limited scalability of the single blockchain framework; and (ii) large communication costs incurred by iterative large-size model update transmission. To this end, we first design an efficient cross-chain framework for scalable and flexible model training management, in which multiple blockchains are customized for specific FL tasks and individually perform learning tasks for privacy protection. A cross-chain scheme is proposed to enable secure blockchain collaboration and interactions for efficient model training, model trading, and payment. We then propose a flexible model update compression scheme to save communication costs almost without compromising accuracy. Moreover, for model trading markets, we design a dynamic pricing scheme using machine learning-based auction for model trading. Numerical results demonstrate that the proposed framework and schemes achieve scalable, flexible, and communication-efficient decentralized FL systems in AIoT.
35
Gradient-based learning applied to document recognition
Yann LeCun, Léon Bottou, Yoshua Bengio et al. · Proceedings of the IEEE · 1998 · 58.2K citations · Full text
HAQ: Hardware-Aware Automated Quantization With Mixed Precision
Kuan Wang, Zhijian Liu, Yujun Lin et al. · 2019 · 940 citations
Paulius Micikevicius, Sharan Narang, Jonah Alben et al. · arXiv (Cornell University) · 2017 · 881 citations · Full text
Deep Gradient Compression: Reducing the Communication Bandwidth for Distributed Training
Yujun Lin, Song Han, Huizi Mao et al. · arXiv (Cornell University) · 2017 · 647 citations · Full text