德尔:消除偏差和控制噪音,以保护隐私的联邦低级调整
IEEE transactions on medical imaging
|March 3, 2025
概括
我们介绍了DEeR,这是一种用于保护隐私的联合学习的新框架,可以增强基础模型适应医疗任务. DEeR有效地消除了聚合偏差,并减轻了差异隐私噪声放大.
科学领域:
- 人工智能的人工智能
- 机器学习 机器学习
- 医疗信息学 医疗信息学
背景情况:
- 联合学习 (FL) 和低级适应 (LoRA) 越来越多地被整合起来,以使基础模型 (FMs) 适应医疗任务,同时保持隐私.
- 结合LoRA和FL的当前方法面临挑战,包括聚合偏差和差异隐私 (DP) 噪声放大.
研究的目的:
- 提出一个新的保护隐私的联邦微调框架,称为偏差消除和噪声调节 (DEeR),以解决聚合偏差和DP噪声放大.
- 从理论上证明消除聚合偏差的条件,并开发一种方法来确保客户之间的LoRA参数等价性.
- 通过解DP噪声和LoRA参数之间的关系来分析和抑制DP增强FL中的噪声放大效应.
主要方法:
- 开发了一个使用交替最小化的偏差消除器,通过优化LoRA参数矩阵来确保零聚合偏差.
- 引入了一个带有两个因子的噪声调节器,以将DP噪声与LoRA参数脱,减轻噪声放大.
- 进行了全面的废弃实验,以验证偏差消除器和噪声调节器的有效性.
主要成果:
- 拟议的DEeR框架在理论上保证并且实际上在联邦微调过程中实现零聚合偏差.
- DEeR有效地抑制了DP-FL固有的噪声放大效应,从而实现了强大的隐私保护.
- 在公共医疗数据集上的实验结果表明,与最先进的方法相比,DEeR的性能优越.
结论:
- 德尔在保护隐私的联邦微调方面取得了重大进展,用于适应医疗领域的基础模型.
- 该框架成功地解决了现有LoRA-FL方法的关键局限性,提供了增强的隐私和性能.
- 拟议的偏差消除和噪声调节策略为现实世界医疗应用提供了强大的解决方案.
相关概念视频
Mean Absolute Deviation
2.6K
The mean absolute deviation is also a measure of the variability of data in a sample. It is the absolute value of the average difference between the data values and the mean.
Let us consider a dataset containing the number of unsold cupcakes in five shops: 10, 15, 8, 7, and 10. Initially, calculate the sample mean. Then calculate the deviation, or the difference, between each data value and the mean. Next, the absolute values of these deviations are added and divided by the sample size to...
Let us consider a dataset containing the number of unsold cupcakes in five shops: 10, 15, 8, 7, and 10. Initially, calculate the sample mean. Then calculate the deviation, or the difference, between each data value and the mean. Next, the absolute values of these deviations are added and divided by the sample size to...
2.6K
Friedman Two-way Analysis of Variance by Ranks
130
Friedman's Two-Way Analysis of Variance by Ranks is a nonparametric test designed to identify differences across multiple test attempts when traditional assumptions of normality and equal variances do not apply. Unlike conventional ANOVA, which requires normally distributed data with equal variances, Friedman's test is ideal for ordinal or non-normally distributed data, making it particularly useful for analyzing dependent samples, such as matched subjects over time or repeated measures...
130
Regression Toward the Mean
6.3K
Regression toward the mean (“RTM”) is a phenomenon in which extremely high or low values—for example, and individual’s blood pressure at a particular moment—appear closer to a group’s average upon remeasuring. Although this statistical peculiarity is the result of random error and chance, it has been problematic across various medical, scientific, financial and psychological applications. In particular, RTM, if not taken into account, can interfere when...
6.3K
Reducing Line Loss
141
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...
141
Residuals and Least-Squares Property
7.2K
The vertical distance between the actual value of y and the estimated value of y. In other words, it measures the vertical distance between the actual data point and the predicted point on the line
If the observed data point lies above the line, the residual is positive, and the line underestimates the actual data value for y. If the observed data point lies below the line, the residual is negative, and the line overestimates the actual data value for y.
The process of fitting the best-fit...
If the observed data point lies above the line, the residual is positive, and the line underestimates the actual data value for y. If the observed data point lies below the line, the residual is negative, and the line overestimates the actual data value for y.
The process of fitting the best-fit...
7.2K
Differential Leveling
115
Differential leveling is a precise method in surveying used to determine the elevation difference between two points. Its primary goal is to establish accurate vertical measurements to create level surfaces or grade lines critical for designing and constructing infrastructures such as roads, bridges, and buildings.The procedure for differential leveling begins with setting up and leveling the instrument at a point where the benchmark can be seen. The level rod is held on the benchmark (BM), and...
115


