FedBM:从预先训练的语言模型中窃取知识,用于异构的联合学习.
Meilu Zhu1, Qiushi Yang2, Zhifan Gao3
1Department of Mechanical Engineering, City University of Hong Kong, Hong Kong Special Administrative Region of China.
Medical image analysis
|March 12, 2025
概括
联合学习 (FL) 面临来自数据异质性的偏见. 我们的FedBM框架使用语言知识和概念引导生成来消除这种偏见,显著提高了医学成像中的模型性能.
科学领域:
- 医疗图像计算 医疗图像计算
- 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) 允许在没有数据隐私泄露的情况下进行协作模式培训.
- 在FL中的数据异质性导致局部学习偏差,降低了整体系统性能.
- 现有的方法很难在异质的联合学习环境中减轻偏见.
研究的目的:
- 引入一个新的框架,联邦偏差消除 (FedBM),以解决异质FL的本地学习偏差.
- 提高处理各种数据分布的联合学习系统的性能和稳定性.
主要方法:
- 基于语言知识的分类器构建 (LKCC):利用类概念,提示和预训练的语言模型 (PLM) 来创建概念嵌入和估计潜在的类分布.
- 概念引导的全球分布估计 (CGDE):采用概念嵌入来训练条件生成器以产生伪数据以校准本地特征提取器.
- 采用冷分类器和发电机校准技术,以防止在本地培训期间出现偏差.
主要成果:
- 美联储BM框架有效地消除了异质联合学习中的本地学习偏见.
- 在公共数据集上的实验结果表明,与最先进的方法相比,性能优越.
- 废弃性研究证实了LKCC和CGDE模块的显著贡献.
结论:
- 在医疗成像的联合学习中,FedBM提供了一个强大的解决方案,以减轻数据异质性的挑战.
- 拟议的方法通过解决本地学习偏差来提高分类器和特征提取器的性能.
- 该框架显示了推进保护隐私和高性能联合学习应用的前景.
相关概念视频
00:56Extraction: Advanced Methods
398
Metal ions can be separated from one another by complexation with organic ligands–the chelating agent– to form uncharged chelates. Here, the chelating agent must contain hydrophobic groups and behave as a weak acid, losing a proton to bind with the metal. Since most organic ligands used in this process are insoluble or undergo oxidation in the aqueous phase, the chelating agent is initially added to the organic phase and extracted into the aqueous phase. The metal-ligand complex is...
398
02:07Improving Translational Accuracy
2.5K
2.5K
01:29Aggregates Classification
297
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...
297
01:26Per-Unit Sequence Models
66
An ideal Y-Y transformer, grounded through neutral impedances, displays per-unit sequence networks akin to those of a single-phase ideal transformer when subjected to balanced positive- or negative-sequence currents. These currents do not produce neutral currents, and their associated voltage drops.
Zero-sequence currents, which are identical in magnitude and phase, generate a neutral current, resulting in voltage drops across the neutral impedance and the low-voltage winding. If the...
Zero-sequence currents, which are identical in magnitude and phase, generate a neutral current, resulting in voltage drops across the neutral impedance and the low-voltage winding. If the...
66
01:27Associative Learning
273
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...
273
02:39lncRNA - Long Non-coding RNAs
2.8K
2.8K