arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2102.02514cs.LGcs.DCstat.ML
收藏

FedAUX:在联邦学习中利用未标记的辅助数据

FedAUX: Leveraging Unlabeled Auxiliary Data in Federated Learning

Fraunhofer HHI(弗劳恩霍夫海因里希·赫兹研究所)

Felix Sattler, Tim Korjakow, Roman Rischke, Wojciech Samek

摘要:

联邦蒸馏(Federated Distillation,FD)是一种流行的新的联邦学习算法范例,它通过将客户端对未标记辅助数据集的预测提取到学生模型中,实现了与先前基于参数平均的方法相竞争的训练性能,同时还允许客户端训练不同的模型架构。在这项工作中,我们提出了FedAUX,FD的扩展,在相同的假设下,通过从未标记的辅助数据中获得最大效用,大大提高了性能。FedAUX以两种方式修改FD训练过程:首先,对辅助数据进行无监督的预训练,以找到分布式训练的模型初始化。其次,$(\varepsilon, δ)$ -差分私有确定性评分用于根据每个客户端模型的确定性对辅助数据上的集合预测进行加权。在大规模卷积神经网络和Transformer模型上进行的实验表明,FedAUX的训练性能在iid和非iid状态下都大大超过了SOTA FL基线方法,进一步缩小了与集中式训练性能的差距。代码可在github.com/fedl-repo/fedaux上获得。

英文摘要:

Federated Distillation (FD) is a popular novel algorithmic paradigm for Federated Learning, which achieves training performance competitive to prior parameter averaging based methods, while additionally allowing the clients to train different model architectures, by distilling the client predictions on an unlabeled auxiliary set of data into a student model. In this work we propose FedAUX, an extension to FD, which, under the same set of assumptions, drastically improves performance by deriving maximum utility from the unlabeled auxiliary data. FedAUX modifies the FD training procedure in two ways: First, unsupervised pre-training on the auxiliary data is performed to find a model initialization for the distributed training. Second, $(\varepsilon, δ)$-differentially private certainty scoring is used to weight the ensemble predictions on the auxiliary data according to the certainty of each client model. Experiments on large-scale convolutional neural networks and transformer models demonstrate, that the training performance of FedAUX exceeds SOTA FL baseline methods by a substantial margin in both the iid and non-iid regime, further closing the gap to centralized training performance. Code is available at github.com/fedl-repo/fedaux.

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。

↑