arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2501.13604cs.LGcs.DC
收藏

FedPref:面向异构多目标偏好的联邦学习

FedPref: Federated Learning Across Heterogeneous Multi-objective Preferences

SnT, University of Luxembourg(卢森堡大学SnT学院);FSTM/DCS, University of Luxembourg(卢森堡大学FSTM/DCS学院)

Maria Hartmann, Grégoire Danoy, Pascal Bouvry

AI总结:

本文提出FedPref,首个面向多目标偏好异构场景的个性化联邦学习算法,并引入多目标指标评估视角,实验证明其性能优于现有算法。

摘要:

联邦学习(FL)是一种分布式机器学习策略,适用于训练数据由分布式设备拥有且无法共享的场景。联邦学习通过在分布式环境中进行模型训练来规避这一限制。这些本地模型的参数会在参与者之间间歇性地共享,并经过聚合以提高模型精度。该策略已被工业界迅速采用,以克服模型训练中的隐私和资源约束。然而,将联邦学习应用于现实世界场景会带来与参与者之间异构性相关的额外挑战。针对联邦学习中缓解这些困难的研究,目前主要集中于两类异构性:训练数据的不均衡分布,以及客户端资源的差异。然而,随着联邦学习的能力扩展至覆盖更复杂的问题(从大语言模型的调优到在边缘设备上实现机器学习),更多类型的异构性正变得日益相关。在本工作中,我们讨论了一种新颖的、在未来应用中可能变得越来越重要的异构性类型:即偏好异构性,当客户端在多个目标下进行学习,且不同客户端对每个目标赋予不同的重要性时,就会出现这种异构性。在本工作中,我们讨论了这类异构性的影响,并提出了FedPref,这是首个在此类场景中实现个性化联邦学习的算法。我们展示了该算法在不同问题、偏好分布和模型架构上的有效性。此外,我们引入了一种基于多目标指标的新分析视角,用于在此类场景中评估联邦学习算法的性能,超越了传统的以客户端为中心的指标。我们基于这一视角进行了第二项实验分析,结果表明FedPref优于对比算法。

英文摘要:

Federated Learning (FL) is a distributed machine learning strategy, developed for settings where training data is owned by distributed devices and cannot be shared. FL circumvents this constraint by carrying out model training in distribution. The parameters of these local models are shared intermittently among participants and aggregated to enhance model accuracy. This strategy has been rapidly adopted by the industry in efforts to overcome privacy and resource constraints in model training. However, the application of FL to real-world settings brings additional challenges associated with heterogeneity between participants. Research into mitigating these difficulties in FL has largely focused on only two types of heterogeneity: the unbalanced distribution of training data, and differences in client resources. Yet more types of heterogeneity are becoming relevant as the capability of FL expands to cover more complex problems, from the tuning of LLMs to enabling machine learning on edge devices. In this work, we discuss a novel type of heterogeneity that is likely to become increasingly relevant in future applications: this is preference heterogeneity, emerging when clients learn under multiple objectives, with different importance assigned to each objective on different clients. In this work, we discuss the implications of this type of heterogeneity and propose FedPref, a first algorithm designed to facilitate personalised FL in this setting. We demonstrate the effectiveness of the algorithm across different problems, preference distributions and model architectures. In addition, we introduce a new analytical point of view, based on multi-objective metrics, for evaluating the performance of FL algorithms in this setting beyond the traditional client-focused metrics. We perform a second experimental analysis based in this view, and show that FedPref outperforms compared algorithms.

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。

↑