arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2607.03334cs.LGcs.AI
收藏

用于HAR的FedAvg:探索个性化与泛化精度之间的权衡

FedAvg for HAR: Exploring the Tradeoff Between Personalized and Generalization Accuracy

IEEE(电气和电子工程师协会)

Andrea De Luna, Susanna Peretti, Chiara Contoli, Alessandro Bogliolo

AI总结:

研究联邦学习中模型个性化与泛化能力的权衡,设计实现多种测试场景,将FedAvg算法用于人类活动识别领域进行实验,呈现结果以了解权衡情况。

摘要:

联邦学习范式促进分布式普适计算与人工智能技术结合,模型在客户端本地设备训练后与中央服务器共享参数,但需权衡模型个性化与泛化能力。本文设计实现多种测试场景评估比较相关范式性能,给出FedAvg算法用于人类活动识别领域的实验结果。

英文摘要:

The federated learning (FL) paradigm fosters distributed pervasive computing combined with artificial intelligence techniques, allowing for optimized data usage and improved mitigation of privacy concerns. Indeed, model training occurs on the client's local devices, and model parameters are subsequently shared with a centralized server. However, there is a need to find a tradeoff between models' personalization and generalization capabilities. In this paper, we design and implement several testing scenarios devoted to evaluating and comparing the centralized, local, and federated paradigm performances. We also design and implement a scenario that emulates a change in clients' data. We then present experimental results of the FedAvg algorithm applied to the Human Activity Recognition (HAR) domain to understand the trade-off between personalized and generalized accuracy. Results show that, although FedAvg confirms a higher degree of personalization capabilities while keeping a high degree of generalization with respect to the traditional centralized learning, this result is not so obvious under stressful conditions, such as when varying class distribution over clients.

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。

↑