基于区块链的联邦集成学习框架，适配医院算力差异。
ChainLearn: A Blockchain-Based Capacity-Aware Framework for Federated Ensemble Learning
- 按医院算力分配不同模型，动态加权集成预测
- 通信开销仅224字节/轮，比FedAvg减少91万倍
- 适合异构算力环境下的医疗影像协作
联邦学习应用于医学影像领域，因隐私限制无法集中数据。传统联邦算法假设硬件同质、架构一致且中心化聚合，在医院算力不均时失效。本文提出容量感知协调机制：测量各医院吞吐量，分配适配的模型（MobileNetV3-Small、EfficientNet-B0、ResNet-50），通过加权集成融合预测结果。弱算力与强算力医院均可参与，无需强制统一架构。将链上策略与链下训练分离：用Solidity合约存储医院注册信息、基准哈希、指标和权重；各医院本地训练后仅提交哈希与标量（不传参数）。加权集成推理在链外完成。在PneumoniaMNIST和DermaMNIST数据集上，5次随机种子、3种非独立同分布水平的实验表明，本方法校准误差低于或等于等权集成，且准确率媲美FedAvg、FedProx和FedMD。每轮通信开销为224字节，较FedAvg降低超过912,000倍。
原文摘要 · Abstract (English)
Federated learning is used in medical imaging where privacy prohibits centralizing data. Standard federated algorithms assume homogeneous hardware, identical architectures, and centralized aggregation, which fails when hospitals have unequal compute resources. We propose capacity-aware coordination: measure each hospital's throughput, assign capacity-appropriate architectures (MobileNetV3-Small, EfficientNet-B0, ResNet-50), and combine predictions via weighted ensemble. Weak and strong hospitals can participate without forcing uniform architectures. We separate on-chain policy from off-chain learning. A Solidity contract stores hospital registration, benchmark hashes, metrics, and weights. Hospitals train locally and submit only hashes and scalars (not parameters). Weighted ensemble inference is computed off-chain. Experiments on PneumoniaMNIST and DermaMNIST (5 seeds, 3 non-IID levels) show our method achieves lower or equal calibration error versus equal-weight ensemble and competitive accuracy versus FedAvg, FedProx, and FedMD. Communication overhead is 224 bytes per round, a reduction of over 912,000x compared to FedAvg.
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。