MP-FedCL：面向边缘智能的多原型联邦对比学习
MP-FedCL: Multiprototype Federated Contrastive Learning for Edge Intelligence
AI总结：
针对联邦学习边缘智能中非独立同分布数据导致模型性能下降的问题，提出多原型联邦对比学习方法MP-FedCL，利用k-means多原型聚合与对比学习提升性能，在多个数据集上平均准确率提升4.6%至10.4%。
摘要：
联邦学习辅助的边缘智能在现代智能服务中实现了隐私保护。然而，边缘客户端之间的非独立同分布（non-IID）数据分布会损害本地模型性能。现有的基于单一原型的策略通过使用特征空间的均值来表示一个类别。然而，特征空间通常不是聚类的，单一原型可能无法很好地表示一个类别。受此启发，本文提出了一种多原型联邦对比学习方法（MP-FedCL），该方法证明了在非独立同分布设置下（包括标签和特征偏斜），使用多原型策略相对于单一原型策略的有效性。具体来说，首先提出了一种基于k-means的多原型计算策略，以捕获每个类别空间的不同嵌入表示，使用多个原型（k个质心）来表示嵌入空间中的一个类别。在每一轮全局通信中，计算得到的多个原型及其各自的模型参数被发送到边缘服务器，聚合成一个全局原型池，然后发送回所有客户端以指导其本地训练。最后，每个客户端的本地训练最小化其自身的监督学习任务，并通过监督对比学习从全局原型池中的共享原型中学习，这鼓励它们从其他客户端学习与自身类别相关的知识，并在每次全局迭代中减少对不相关知识的吸收。在MNIST、Digit-5、Office-10和DomainNet上的实验结果表明，我们的方法优于多个基线，在特征和标签非独立同分布下，平均测试准确率分别提高了约4.6%和10.4%。
英文摘要：
Federated learning-assisted edge intelligence enables privacy protection in modern intelligent services. However, not independent and identically distributed (non-IID) distribution among edge clients can impair the local model performance. The existing single prototype-based strategy represents a class by using the mean of the feature space. However, feature spaces are usually not clustered, and a single prototype may not represent a class well. Motivated by this, this paper proposes a multi-prototype federated contrastive learning approach (MP-FedCL) which demonstrates the effectiveness of using a multi-prototype strategy over a single-prototype under non-IID settings, including both label and feature skewness. Specifically, a multi-prototype computation strategy based on \textit{k-means} is first proposed to capture different embedding representations for each class space, using multiple prototypes ($k$ centroids) to represent a class in the embedding space. In each global round, the computed multiple prototypes and their respective model parameters are sent to the edge server for aggregation into a global prototype pool, which is then sent back to all clients to guide their local training. Finally, local training for each client minimizes their own supervised learning tasks and learns from shared prototypes in the global prototype pool through supervised contrastive learning, which encourages them to learn knowledge related to their own class from others and reduces the absorption of unrelated knowledge in each global iteration. Experimental results on MNIST, Digit-5, Office-10, and DomainNet show that our method outperforms multiple baselines, with an average test accuracy improvement of about 4.6\% and 10.4\% under feature and label non-IID distributions, respectively.
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。
