Assessing the Impacts of Imperfect Datasets on Client Selections in Federated Learning

AI 中文解读

联邦学习最近有了新发现：数据质量差的客户端，可能拖累整个AI模型的训练效果。这项研究指出，不同客户端的数据往往“长短不一、好坏参半”，比如有人数据量少，有人标签不准确，如果一视同仁地训练，模型不仅学得慢，准确率还会下降。但简单粗暴地剔除这些客户端，又可能造成偏见，影响整体公平性。研究团队设计了一套兼顾隐私的评分方法，能评估每个客户端的真实贡献，从而让联邦学习更高效、更公正。这项技术对普通人的意义在于，未来手机输入法、健康监测等应用在利用分布式数据训练AI时，即使部分用户数据不完美，整体模型也能保持稳定和准确，同时个人数据不用上传，隐私更有保障。

Federated learning (FL) is a popular distributed learning framework where multiple clients perform local training and a server aggregates the locally updated models. FL enables decentralized training while preserving the privacy of clients' datasets. However, non-independent and identically distributed (non-IID) or noisy datasets can lead to low model accuracy or high convergence latency. Precluding these clients through client selection may mitigate the problem, but heavily biased client selections may also degrade the learning performance. In this study, we first experimentally measure the impact of non-IID data (including skews in data quantity and label distribution), noisy data, and fairness in client selection on model accuracy and convergence. We then propose a privacy-preserving scoring method to assess each client's contribution in FL, with experiments conducted to demonstrate the effectiveness of the proposed assessment.