一个与大小内核注意力网络的联合学习,用于图像分类
Tianzhe Liu1, Jing Xie2, Heng Dong3
1Fujian Police College, Fuzhou, China.
Frontiers in plant science
|March 9, 2026
概括
本研究介绍了FL-LSNet,一个使用大小网络 (LSNet) 的联合学习 (FL) 框架,以提高协作学习中的数据安全性和性能. FL-LSNet 提高了准确性,并减少了各种应用的计算负载.
科学领域:
- 计算机科学 计算机科学
- 人工智能的人工智能
- 机器学习 机器学习
背景情况:
- 联合学习 (FL) 面临异质图像数据的挑战,影响安全,隐私和性能.
- 现有的FL框架在复杂的图像特性和平衡协作与数据安全方面扎.
研究的目的:
- 介绍FL-LSNet,这是一个新的联合学习框架,具有轻量级的大小网络 (LSNet).
- 在协作图像学习中解决数据安全,隐私和性能退化问题.
主要方法:
- 开发了FL-LSNet,采用客户端-服务器架构来实现分散的预处理和数据隐私.
- 集成的LSNet,用于全球环境的大型内核感知器 (LKP) 和用于本地融合的小型内核注意力 (SKA).
- 实现了对长尾数据和服务器端聚合的动态权重调整.
主要成果:
- 与Swin变压器和基线模型相比,LSNet减少了7%的计算开销,并提高了19%的功能表示.
- 在三个数据集上,FL-LSNet的表现优于FedAvg和MOON,准确度达到84.32%至98.92%.
- 废弃性研究表明,FedAvg-LSNet集成超过了基线6.15%.
结论:
- 在联合学习中,FL-LSNet提供了一个可扩展的解决方案,用于多利益相关方的数据协作.
- 介绍了FL用于公共安全,农业和医学诊断的轻量级垂直适应的新见解.
相关概念视频
Introduction to Learning
1.3K
Learning is the process of acquiring knowledge or skills through practice or experience, leading to long-lasting behavioral changes. This acquisition occurs through interaction with the environment and requires practice or experience. For instance, mastering a skill such as surfing requires considerable practice and experience, highlighting the essential role of repeated interactions with the environment in learning.
In contrast to learned behaviors, unlearned behaviors such as crying, sexual...
In contrast to learned behaviors, unlearned behaviors such as crying, sexual...
1.3K
Force Classification
2.6K
Forces play a crucial role in the study of physics and engineering. They are essential in describing the motion, behavior, and equilibrium of objects in the physical world. Forces can be classified based on their origin, type, and direction of action.
Contact and non-contact forces are two of the most widely used categories of forces. As the name suggests, contact forces require physical contact between two objects to act upon each other. Examples of contact forces include frictional,...
Contact and non-contact forces are two of the most widely used categories of forces. As the name suggests, contact forces require physical contact between two objects to act upon each other. Examples of contact forces include frictional,...
2.6K
Association Areas of the Cortex
10.2K
Association areas are regions of the cerebral cortex that do not have a specific sensory or motor function. Instead, they integrate and interpret information from various sources to enable higher cognitive processes such as memory, learning, and decision-making. Some key association areas include the following:
Prefrontal Association Area: This area is located in the frontal lobe and is involved in planning, decision-making, and moderating social behavior. It connects with primary motor areas,...
Prefrontal Association Area: This area is located in the frontal lobe and is involved in planning, decision-making, and moderating social behavior. It connects with primary motor areas,...
10.2K

