RSCFed：随机抽样共识联邦半监督学习
RSCFed: Random Sampling Consensus Federated Semi-supervised Learning
摘要：
联邦半监督学习（Federated semi-supervised learning，FSSL）的目标是通过训练完全标记和完全未标记的客户端或训练部分标记的客户端来获得全局模型。当本地客户端具有独立且相同分布（IID）数据时，现有方法工作良好，但不能推广到更实际的FSSL设置，即，非IID设置。针对完全标记、完全未标记和部分标记客户端模型之间的不均匀可靠性，提出了一种随机抽样共识联邦学习（RSCFed）.我们的主要动机是，给定的模型与标记的客户端或未标记的客户端有很大的偏差，可以通过对客户端进行随机子采样来达成共识。为了实现这一点，我们不是直接聚合局部模型，而是首先通过对客户端进行随机子采样来提取几个子共识模型，然后将子共识模型聚合到全局模型中。为了提高亚一致性模型的鲁棒性，我们还提出了一种新的距离重新加权的模型聚合方法。实验结果表明，我们的方法优于国家的最先进的方法在三个基准数据集，包括自然和医学图像。该代码可在https://github.com/XMed-Lab/RSCFed上获得。
英文摘要：
Federated semi-supervised learning (FSSL) aims to derive a global model by training fully-labeled and fully-unlabeled clients or training partially labeled clients. The existing approaches work well when local clients have independent and identically distributed (IID) data but fail to generalize to a more practical FSSL setting, i.e., Non-IID setting. In this paper, we present a Random Sampling Consensus Federated learning, namely RSCFed, by considering the uneven reliability among models from fully-labeled clients, fully-unlabeled clients or partially labeled clients. Our key motivation is that given models with large deviations from either labeled clients or unlabeled clients, the consensus could be reached by performing random sub-sampling over clients. To achieve it, instead of directly aggregating local models, we first distill several sub-consensus models by random sub-sampling over clients and then aggregating the sub-consensus models to the global model. To enhance the robustness of sub-consensus models, we also develop a novel distance-reweighted model aggregation method. Experimental results show that our method outperforms state-of-the-art methods on three benchmarked datasets, including both natural and medical images. The code is available at https://github.com/XMed-Lab/RSCFed.
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。
