论文标题
跨晶型标签的传播，用于转导和半监督联盟学习
Cross-client Label Propagation for Transductive and Semi-Supervised Federated Learning
论文作者
论文摘要
我们提出了跨客户标签传播（XCLP），这是一种新的转导联合学习方法。 XCLP通过多个客户的数据共同估算数据图，并通过在图表上传播标签信息来计算未标记数据的标签。为了避免客户必须与任何人共享他们的数据，XCLP采用了两个密码安全的协议：安全锤距距离计算和安全求和。我们演示了XCLP在联合学习中的两个不同的应用。首先，我们以一种单发的方式使用它来预测看不见的测试点的标签。在第二个中，我们使用它在联合半监督的环境中反复伪造标签未标记的训练数据。对实际联合和标准基准数据集的实验表明，在这两个应用程序中，XCLP都比替代方法都具有更高的分类精度。
We present Cross-Client Label Propagation(XCLP), a new method for transductive federated learning. XCLP estimates a data graph jointly from the data of multiple clients and computes labels for the unlabeled data by propagating label information across the graph. To avoid clients having to share their data with anyone, XCLP employs two cryptographically secure protocols: secure Hamming distance computation and secure summation. We demonstrate two distinct applications of XCLP within federated learning. In the first, we use it in a one-shot way to predict labels for unseen test points. In the second, we use it to repeatedly pseudo-label unlabeled training data in a federated semi-supervised setting. Experiments on both real federated and standard benchmark datasets show that in both applications XCLP achieves higher classification accuracy than alternative approaches.
