FedNolowe:一种基于损失的规范化加权聚合策略,用于在异质环境中实现强大的联合学习
Duy-Dong Le1, Tuong-Nguyen Huynh1, Anh-Khoa Tran2
1Industrial University of Ho Chi Minh City (IUH), Ho Chi Minh City, Vietnam.
PloS one
|August 14, 2025
概括
联邦规范化基于损失的加权聚合 (FedNolowe) 通过使用规范化培训损失来加权客户贡献来提高联邦学习稳定性. 这种方法增强了模型的融合,并减少了计算复杂性,以在不同的数据设置中获得更好的性能.
科学领域:
- 机器学习 机器学习
- 分布式系统 分布式系统
- 数据科学数据科学数据科学
背景情况:
- 联合学习 (FL) 允许在分散的数据上进行协作模式培训.
- 跨客户的非独立和相同分布 (非IID) 数据挑战了FL的融合和稳定性.
- 现有的方法通常依赖于数据集大小或是计算密集的.
研究的目的:
- 为稳定的FL引入基于损失的联邦规范化权重聚合 (FedNolowe).
- 为了应对FL中非IID数据所带来的挑战.
- 与现有的FL聚合方法相比,以减少计算复杂性.
主要方法:
- 提出FedNolowe,一种新的聚合方法,使用规范化训练损失来对客户进行加权.
- 实施两阶段L1规范化技术来实现损失规范化.
- 在异质和IID环境中评估FedNolowe的性能和稳定性.
主要成果:
- 实际上,FedNolowe根据正常化的培训损失有效地权衡客户贡献,有利于损失较低的客户.
- 拟议的两阶段L1规范化在浮点运算中将计算复杂度降低40%.
- 在非IID场景中,FedNolowe实现了最先进的业绩,并证明了在非IID场景中增强的稳定性.
结论:
- FedNolowe为联合学习提供了一种计算效率高,稳定的聚合方法.
- 敏感性分析证实了FedNolowe在异质数据分布中的稳定性.
- 在现实世界FL应用中,FedNolowe提供了一种改善全球模型性能的实用解决方案.
相关概念视频
Weighted Mean
5.3K
While taking the arithmetic, geometric, or harmonic mean of a sample data set, equal importance is assigned to all the data points. However, all the values may not always be equally important in some data sets. An intrinsic bias might make it more important to give more weightage to specific values over others.
For example, consider the number of goals scored in the matches of a tournament. While computing the average number of goals scored in the tournament, it may be more important to...
For example, consider the number of goals scored in the matches of a tournament. While computing the average number of goals scored in the tournament, it may be more important to...
5.3K
Aggregates Classification
381
Aggregate classification is generally based on its size, petrographic characteristics, weight, and source. Size classification ranges from coarse to fine aggregates, defined by the size of the particles. Coarse aggregates are particles that do not pass through ASTM sieve No. 4, and aggregates that pass through the sieve are fine aggregates.
Petrographic classification groups aggregates based on common mineralogical characteristics. Some of the common mineral groups found in aggregates are...
Petrographic classification groups aggregates based on common mineralogical characteristics. Some of the common mineral groups found in aggregates are...
381
Reducing Line Loss
193
In a three-phase circuit, line loss is an indicator of energy dissipated as heat due to the resistance of transmission lines. To address this, incorporating transformers into the system—a step-up transformer at the source and a step-down transformer at the load—is a strategic solution. Two three-phase transformers are introduced to improve this.
With a step-up transformer at the source, the voltage is increased, thereby reducing the current in the transmission lines since power loss...
With a step-up transformer at the source, the voltage is increased, thereby reducing the current in the transmission lines since power loss...
193
Unsoundness of Aggregate due to Volume Change
177
Unsoundness in aggregates due to volume changes is primarily caused by the physical alterations aggregates undergo, such as freezing and thawing, thermal changes, and wetting and drying. Unsound aggregates, when subjected to these changes, result in volume change upon disintegration. This, in turn, contributes to the deterioration of concrete, including scaling, pop-outs, and cracking. Particular types of aggregates, such as porous flints, cherts, and those containing clay minerals, are...
177
Improving Translational Accuracy
2.7K
2.7K
Associative Learning
575
Associative learning is a fundamental concept in behavioral psychology, wherein a connection is established between two stimuli or events, leading to a learned response. This process is critical in understanding how behaviors are acquired and modified. Conditioning, the mechanism through which associations are formed, can be divided into two main types: classical conditioning and operant conditioning, each elucidating different aspects of associative learning.
Classical conditioning, also known...
Classical conditioning, also known...
575
