改进联邦学习聚合方法，提升模型收敛速度与稳定性。
FedPID: An Aggregation Method for Federated Learning
- 借鉴PID控制器思想，结合样本量与损失下降率加权聚合。
- 通过泊松分布调整训练轮次，缓解数据规模差异带来的偏差。
- 新积分项基于全局损失下降，更稳定捕捉训练进展。
本文提出 FedPID，作为联邦肿瘤分割挑战赛 2024（FETS24）的参赛方案。受 FedCostWAvg 与 FedPIDAvg 的启发，我们设计了一种改进的联邦学习聚合策略。FedCostWAvg 通过考虑各参与方的样本数量及上轮训练中损失函数的下降幅度进行加权平均，类比于 PID 控制器的微分部分。在 FedPIDAvg 中，我们补充了缺失的积分项。面对各中心数据集规模差异巨大的问题，我们假设数据规模服从泊松分布，并据此动态调整各中心的训练轮次，以降低极端大样本中心对训练过程的干扰。在此基础上，我们进一步优化了积分项的计算方式：不再累积局部损失，而是测量自首轮以来的全局损失下降量，从而更准确反映整体训练进度。
原文摘要 · Abstract (English)
This paper presents FedPID, our submission to the Federated Tumor Segmentation Challenge 2024 (FETS24). Inspired by FedCostWAvg and FedPIDAvg, our winning contributions to FETS21 and FETS2022, we propose an improved aggregation strategy for federated and collaborative learning. FedCostWAvg is a method that averages results by considering both the number of training samples in each group and how much the cost function decreased in the last round of training. This is similar to how the derivative part of a PID controller works. In FedPIDAvg, we also included the integral part that was missing. Another challenge we faced were vastly differing dataset sizes at each center. We solved this by assuming the sizes follow a Poisson distribution and adjusting the training iterations for each center accordingly. Essentially, this part of the method controls that outliers that require too much training time are less frequently used. Based on these contributions we now adapted FedPIDAvg by changing how the integral part is computed. Instead of integrating the loss function we measure the global drop in cost since the first round.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。