标题： 谁可以信任？ 基于Logit的联邦学习中聚合客户端知识 显示英文标题

标题： Who to Trust? Aggregating Client Knowledge in Logit-Based Federated Learning

摘要： 联邦学习（FL）通常共享模型权重或梯度，这对大型模型来说成本较高。基于日志的FL通过仅共享在公共代理数据集上计算的日志来降低此成本。然而，从异构客户端聚合信息仍然是一个挑战。本文研究了这个问题，介绍了并比较了三种日志聚合方法：简单平均、不确定性加权平均和一个学习的元聚合器。在MNIST和CIFAR-10上进行评估，这些方法减少了通信开销，在非独立同分布数据下提高了鲁棒性，并实现了与集中训练相当的准确性。 显示英文摘要

摘要： Federated learning (FL) usually shares model weights or gradients, which is costly for large models. Logit-based FL reduces this cost by sharing only logits computed on a public proxy dataset. However, aggregating information from heterogeneous clients is still challenging. This paper studies this problem, introduces and compares three logit aggregation methods: simple averaging, uncertainty-weighted averaging, and a learned meta-aggregator. Evaluated on MNIST and CIFAR-10, these methods reduce communication overhead, improve robustness under non-IID data, and achieve accuracy competitive with centralized training.