FedTGP：用于联邦学习中数据与模型异质性的自适应边距增强对比学习可训练全局原型
FedTGP: Trainable Global Prototypes with Adaptive-Margin-Enhanced Contrastive Learning for Data and Model Heterogeneity in Federated Learning
AI总结：
针对异构联邦学习中原型加权平均聚合导致全局知识欠佳的问题，提出FedTGP方法，利用自适应边距增强对比学习在服务器端学习可训练全局原型，在十二个异构模型上准确率最高提升9.08%。
摘要：
近期，异构联邦学习（Heterogeneous Federated Learning, HtFL）因支持异构模型与数据的能力而备受关注。为降低HtFL中传输模型参数的高通信成本这一主要挑战，基于原型的HtFL方法被提出，该方法仅在异构客户端间共享类代表（即原型），同时保护客户端模型隐私。然而，这些原型在服务器上通过加权平均简单聚合为全局原型，导致全局知识欠佳，负面影响客户端性能。为克服此挑战，我们引入名为FedTGP的新型HtFL方法，利用我们提出的自适应边距增强对比学习（Adaptive-margin-enhanced Contrastive Learning, ACL）在服务器上学习可训练全局原型（Trainable Global Prototypes, TGP）。通过结合ACL，我们的方法在保留语义的同时增强了原型可分性。在十二个异构模型上的大量实验表明，我们的FedTGP在准确率上超越现有最先进方法高达9.08%，同时保持了基于原型的HtFL在通信与隐私方面的优势。代码可在 https://github.com/TsingZ0/FedTGP 获取。
英文摘要：
Recently, Heterogeneous Federated Learning (HtFL) has attracted attention due to its ability to support heterogeneous models and data. To reduce the high communication cost of transmitting model parameters, a major challenge in HtFL, prototype-based HtFL methods are proposed to solely share class representatives, a.k.a, prototypes, among heterogeneous clients while maintaining the privacy of clients' models. However, these prototypes are naively aggregated into global prototypes on the server using weighted averaging, resulting in suboptimal global knowledge which negatively impacts the performance of clients. To overcome this challenge, we introduce a novel HtFL approach called FedTGP, which leverages our Adaptive-margin-enhanced Contrastive Learning (ACL) to learn Trainable Global Prototypes (TGP) on the server. By incorporating ACL, our approach enhances prototype separability while preserving semantic meaning. Extensive experiments with twelve heterogeneous models demonstrate that our FedTGP surpasses state-of-the-art methods by up to 9.08% in accuracy while maintaining the communication and privacy advantages of prototype-based HtFL. Our code is available at https://github.com/TsingZ0/FedTGP.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
