联邦聚合与层间个性化贡献:基于偏好的优化,性能与隐私之间的优化
相关实验视频
Updated: May 9, 2025

06:48
The HoneyComb Paradigm for Research on Collective Human Behavior
Published on: January 19, 2019
9.3K
IEEE transactions on neural networks and learning systems
|April 30, 2025
概括
本研究介绍了FedIPC和FedAPI-NSGA-II的个性化联合学习 (PFL). 这些方法通过考虑内部层贡献和用户偏好来改善模型聚合,以获得更好的性能和隐私平衡.
科学领域:
- 人工智能的人工智能
- 机器学习 机器学习
- 分布式系统 分布式系统
背景情况:
- 个性化联合学习 (PFL) 解决了用户之间的数据异质性.
- 现有的PFL方法在聚合过程中忽略了层间贡献.
- 将用户隐私和模型性能与定性偏好的平衡是具有挑战性的.
研究的目的:
- 提出一个联邦聚合框架 (FedIPC),考虑层间的贡献.
- 开发一个多目标优化方法 (FedAPI-NSGA-II) 用于适应性偏好匹配.
- 通过提高模型性能和与用户偏好保持一致来增强PFL.
主要方法:
- 联邦聚合与层间个性化贡献 (FedIPC) 框架.
- 使用自适应偏好指标和NSGA-II.II的多目标优化.
- 对图像和表格数据集进行了广泛的实验.
主要成果:
- 在联合学习中加速模型融合.
- 对整体模型性能进行了显著的改进.
- 用户偏好的有效匹配,以实现隐私与性能之间的权衡.
结论:
- 通过纳入层间贡献,FedIPC增强了PFL.
- FedAPI-NSGA-II成功地平衡了模型性能和用户定义的隐私偏好.
- 提出的方法为个性化联合学习提供了强大的解决方案.
相关概念视频
Maximum Size of Aggregate
56
The maximum size of aggregate is defined as the aperture of the sieve retaining 15 percent or more of the particles present in the aggregate sample. The aggregate's maximum size impacts the concrete's water requirement, workability, and strength. Larger aggregates reduce the surface area needing cement paste coverage, which can lower water needs, thereby allowing a decrease in the water-to-cement ratio when the desired workability and richness of the mix are to be maintained, which can...
56
In- and Out-Groups
38.5K
People all belong to a gender, race, age, and social economic group. These groups provide a powerful source of our identity and self-esteem (Tajfel & Turner, 1979) and serve as our in-groups. An in-group is a group that we identify with or see ourselves as belonging to.
38.5K
Social Exchange Theory
34.0K
We have discussed why we form relationships, what attracts us to others, and different types of love. But what determines whether we are satisfied with and stay in a relationship? One theory that provides an explanation is social exchange theory. According to social exchange theory, we act as naïve economists in keeping a tally of the ratio of costs and benefits of forming and maintaining a relationship with others (Rusbult & Van Lange, 2003).
34.0K
Optimal Foraging
11.8K
How animals obtain and eat their food is called foraging behavior. Foraging can include searching for plants and hunting for prey and depends on the species and environment.
11.8K
Aggregates Classification
289
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...
289
Social Loafing
34.3K
Another way in which a group presence can affect performance is social loafing—the exertion of less effort by a person working together with a group. Social loafing occurs when our individual performance cannot be evaluated separately from the group. Thus, group performance declines on easy tasks (Karau & Williams, 1993). Essentially individual group members loaf and let other group members pick up the slack. Because each individual’s efforts cannot be evaluated,...
34.3K

