基于区块链的去中心化联邦分片学习，兼顾隐私与高效训练。
HLF-FSL. A Decentralized Federated Split Learning Solution for IoT on Hyperledger Fabric
- 用区块链协调分片模型训练，无中心服务器
- 在CIFAR-10和MNIST上达到与集中式相当精度
- 适合对隐私和可扩展性要求高的企业级物联网场景
敏感领域中的协同机器学习需要可扩展、保隐私的企业级解决方案。传统联邦学习依赖中心服务器，存在单点故障和隐私风险；分片学习虽能分割模型保护隐私，但因训练串行导致扩展性差。本文提出一种结合联邦分片学习（FSL）与许可链Hyperledger Fabric（HLF）的去中心化架构。链码在无中心协调下执行分片模型并实现点对点聚合，利用HLF的瞬态字段和私有数据集合（PDCs）保障原始数据与模型激活的隐私。在CIFAR-10和MNIST基准测试中，HLF-FSL达到与集中式FSL相当的准确率，且每轮训练时间优于基于以太坊的工作。性能与可扩展性测试显示区块链开销极小，准确率保持不变，证明其具备企业级可行性。
原文摘要 · Abstract (English)
Collaborative machine learning in sensitive domains demands scalable, privacy preserving solutions for enterprise deployment. Conventional Federated Learning (FL) relies on a central server, introducing single points of failure and privacy risks, while Split Learning (SL) partitions models for privacy but scales poorly due to sequential training. We present a decentralized architecture that combines Federated Split Learning (FSL) with the permissioned blockchain Hyperledger Fabric (HLF). Our chaincode orchestrates FSL's split model execution and peer-to-peer aggregation without any central coordinator, leveraging HLF's transient fields and Private Data Collections (PDCs) to keep raw data and model activations private. On CIFAR-10 and MNIST benchmarks, HLF-FSL matches centralized FSL accuracy while reducing per epoch training time compared to Ethereum-based works. Performance and scalability tests show minimal blockchain overhead and preserved accuracy, demonstrating enterprise grade viability.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。