公平表示学习持续敏感属性使用预期的整体概率指标的学习
概括
这项研究引入了一个新的AI公平算法,用于持续敏感的属性,如年龄. 建议使用EIPM与MMD (FREM) 方法的公平代表有效减少偏见,优于现有的方法.
科学领域:
- 人工智能的人工智能
- 机器学习 机器学习
- 数据科学数据科学数据科学
背景情况:
- 人工智能公平,或算法公平,旨在防止人工智能系统中的偏见.
- 公平代表性学习 (FRL) 是一个关键的方法,但当前的方法与持续敏感的属性 (例如年龄,收入) 斗争.
研究的目的:
- 开发一种新的公平代表学习 (FRL) 算法,能够处理连续的敏感属性.
- 在具有连续属性的代表空间中引入评估公平性的新指标.
主要方法:
- 引入了整体概率指标的预期 (EIPM) 来量化连续属性的公平性.
- 从有限的样本中开发了一种准确估计EIPM的方法.
- 提出了一个新的FRL算法,公平代表使用EIPM与MMD (FREM),利用EIPM.
主要成果:
- 证明了在代表空间中低EIPM值可以确保公平,无论预测头部如何.
- 展示了FREM有效地处理连续敏感属性.
- 实验结果表明,FREM在AI公平性方面优于现有的基线方法.
结论:
- 拟议的EIPM指标和FREM算法为实现AI公平性提供了强大的解决方案,具有连续敏感属性.
- 与现有的FRL技术相比,FREM提供了显著的进步,使公平AI的更广泛应用成为可能.
相关概念视频
Prediction Intervals
2.2K
The interval estimate of any variable is known as the prediction interval. It helps decide if a point estimate is dependable.
However, the point estimate is most likely not the exact value of the population parameter, but close to it. After calculating point estimates, we construct interval estimates, called confidence intervals or prediction intervals. This prediction interval comprises a range of values unlike the point estimate and is a better predictor of the observed sample value, y.
However, the point estimate is most likely not the exact value of the population parameter, but close to it. After calculating point estimates, we construct interval estimates, called confidence intervals or prediction intervals. This prediction interval comprises a range of values unlike the point estimate and is a better predictor of the observed sample value, y.
2.2K
Probability in Statistics
12.3K
Probability is the likelihood of an event occurring. The term event is defined as a collection of results of a procedure. An event is a simple event when an outcome cannot be divided into simpler parts.
An example of a simple event is a coin toss. The result of a coin toss is either a head or a tail. Here, head and tail are two simple events. These two simple events make up the sample space. Further, the probability of an event occurring falls within the range of 0 to 1. The probability of an...
An example of a simple event is a coin toss. The result of a coin toss is either a head or a tail. Here, head and tail are two simple events. These two simple events make up the sample space. Further, the probability of an event occurring falls within the range of 0 to 1. The probability of an...
12.3K
Probability Laws
39.6K
Overview
39.6K
Expected Value
3.8K
The expected value is known as the "long-term" average or mean. This means that over the long term of experimenting over and over, you would expect this average. The expected average is represented by the symbol μ. It is calculated as follows:
3.8K
Sampling Continuous Time Signal
195
In signal processing, a continuous-time signal can be sampled using an impulse-train sampling technique, followed by the zero-order hold method. Impulse-train sampling involves the use of a periodic impulse train, which consists of a series of delta functions spaced at regular intervals determined by the sampling period. When a continuous-time signal is multiplied by this impulse train, it generates impulses with amplitudes corresponding to the signal's values at the sampling points.
In the...
In the...
195
Probability Histograms
11.0K
A probability histogram is a visual representation of a probability distribution. Similar a typical histogram, the probability histogram consists of contiguous (adjoining) boxes. It has both a horizontal axis and a vertical axis. The horizontal axis is labeled with what the data represents. The vertical axis is labeled with probability. Each rectangular bar in the histogram is 1 unit wide, which suggests that the area under each bar equals the probability, P(x), where x is 1, 2, 3, and so on.
11.0K


