arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2310.02420cs.LGcs.CVcs.DC
收藏

FedL2P: 联邦学习个性化方法

FedL2P: Federated Learning to Personalize

University of Cambridge(剑桥大学);Samsung AI Center(三星人工智能中心);University of Edinburgh(爱丁堡大学);Flower Labs(Flower实验室)

Royson Lee, Minyoung Kim, Da Li, Xinchi Qiu, Timothy Hospedales, Ferenc Huszár, Nicholas D. Lane

AI总结:

针对联邦学习中通用个性化策略适配性不足的问题,提出FedL2P框架,通过联邦元学习训练元网络为各客户端生成定制化的批归一化和学习率参数,在标签与特征偏移场景下性能优于多种人工设计基线。

摘要:

联邦学习(FL)研究在全局模型分布式学习算法、以及针对各客户端本地数据分布特性对通用模型进行本地个性化的算法方面已取得进展。但不同的FL问题可能需要不同的个性化策略,甚至无法为所有客户端定义一种有效的通用个性化策略:根据各客户端最优预测器与全局模型预测器的相似程度,可能需要采用不同的个性化策略。本文研究学习个性化策略的联邦元学习问题,具体而言,我们采用元网络,可根据本地数据统计量为每个客户端生成批归一化(batch-norm)参数和学习率参数。通过联邦学习训练这些元网络,整个FL网络可协同学习为每个客户端定制的个性化策略。实验结果表明,在标签偏移和特征偏移场景下,该框架均优于多种标准人工设计的个性化基线方法。

英文摘要:

Federated learning (FL) research has made progress in developing algorithms for distributed learning of global models, as well as algorithms for local personalization of those common models to the specifics of each client's local data distribution. However, different FL problems may require different personalization strategies, and it may not even be possible to define an effective one-size-fits-all personalization strategy for all clients: depending on how similar each client's optimal predictor is to that of the global model, different personalization strategies may be preferred. In this paper, we consider the federated meta-learning problem of learning personalization strategies. Specifically, we consider meta-nets that induce the batch-norm and learning rate parameters for each client given local data statistics. By learning these meta-nets through FL, we allow the whole FL network to collaborate in learning a customized personalization strategy for each client. Empirical results show that this framework improves on a range of standard hand-crafted personalization baselines in both label and feature shift situations.

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。

↑