اشترك بالحزمة الذهبية واحصل على وصول غير محدود شمرا أكاديميا
تسجيل مستخدم جديدGradual (In)Compatibility of Fairness Criteria
36
0
0.0
(
0
)
اسأل ChatGPT حول البحث
ﻻ يوجد ملخص باللغة العربية
Impossibility results show that important fairness measures (independence, separation, sufficiency) cannot be satisfied at the same time under reasonable assumptions. This paper explores whether we can satisfy and/or improve these fairness measures simultaneously to a certain degree. We introduce information-theoretic formulations of the fairness measures and define degrees of fairness based on these formulations. The information-theoretic formulations suggest unexplored theoretical relations between the three fairness measures. In the experimental part, we use the information-theoretic expressions as regularizers to obtain fairness-regularized predictors for three standard datasets. Our experiments show that a) fairness regularization directly increases fairness measures, in line with existing work, and b) some fairness regularizations indirectly increase other fairness measures, as suggested by our theoretical findings. This establishes that it is possible to increase the degree to which some fairness measures are satisfied at the same time -- some fairness measures are gradually compatible.
قيم البحث
اقرأ أيضاً
Fairness in algorithmic decision-making processes is attracting increasing concern. When an algorithm is applied to human-related decision-making an estimator solely optimizing its predictive power can learn biases on the existing data, which motivat
es us the notion of fairness in machine learning. while several different notions are studied in the literature, little studies are done on how these notions affect the individuals. We demonstrate such a comparison between several policies induced by well-known fairness criteria, including the color-blind (CB), the demographic parity (DP), and the equalized odds (EO). We show that the EO is the only criterion among them that removes group-level disparity. Empirical studies on the social welfare and disparity of these policies are conducted.
Dimensionality reduction is a classical technique widely used for data analysis. One foundational instantiation is Principal Component Analysis (PCA), which minimizes the average reconstruction error. In this paper, we introduce the multi-criteria di
mensionality reduction problem where we are given multiple objectives that need to be optimized simultaneously. As an application, our model captures several fairness criteria for dimensionality reduction such as our novel Fair-PCA problem and the Nash Social Welfare (NSW) problem. In Fair-PCA, the input data is divided into $k$ groups, and the goal is to find a single $d$-dimensional representation for all groups for which the minimum variance of any one group is maximized. In NSW, the goal is to maximize the product of the individual variances of the groups achieved by the common low-dimensional space. Our main result is an exact polynomial-time algorithm for the two-criterion dimensionality reduction problem when the two criteria are increasing concave functions. As an application of this result, we obtain a polynomial time algorithm for Fair-PCA for $k=2$ groups and a polynomial time algorithm for NSW objective for $k=2$ groups. We also give approximation algorithms for $k>2$. Our technical contribution in the above results is to prove new low-rank properties of extreme point solutions to semi-definite programs. We conclude with experiments indicating the effectiveness of algorithms based on extreme point solutions of semi-definite programs on several real-world data sets.
Recommender systems are being employed across an increasingly diverse set of domains that can potentially make a significant social and individual impact. For this reason, considering fairness is a critical step in the design and evaluation of such s
ystems. In this paper, we introduce HyperFair, a general framework for enforcing soft fairness constraints in a hybrid recommender system. HyperFair models integrate variations of fairness metrics as a regularization of a joint inference objective function. We implement our approach using probabilistic soft logic and show that it is particularly well-suited for this task as it is expressive and structural constraints can be added to the system in a concise and interpretable manner. We propose two ways to employ the methods we introduce: first as an extension of a probabilistic soft logic recommender system template; second as a fair retrofitting technique that can be used to improve the fairness of predictions from a black-box model. We empirically validate our approach by implementing multiple HyperFair hybrid recommenders and compare them to a state-of-the-art fair recommender. We also run experiments showing the effectiveness of our methods for the task of retrofitting a black-box model and the trade-off between the amount of fairness enforced and the prediction performance.
In this paper, we apply techniques of ensemble analysis to understand the political baseline for Congressional representation in Colorado. We generate a large random sample of reasonable redistricting plans and determine the partisan balance of each
district using returns from state-wide elections in 2018, and analyze the 2011/2012 enacted districts in this context. Colorado recently adopted a new framework for redistricting, creating an independent commission to draw district boundaries, prohibiting partisan bias and incumbency considerations, requiring that political boundaries (such as counties) be preserved as much as possible, and also requiring that mapmakers maximize the number of competitive districts. We investigate the relationships between partisan outcomes, number of counties which are split, and number of competitive districts in a plan. This paper also features two novel improvements in methodology--a more rigorous statistical framework for understanding necessary sample size, and a weighted-graph method for generating random plans which split approximately as few counties as acceptable human-drawn maps.
We initiate the study of fairness in reinforcement learning, where the actions of a learning algorithm may affect its environment and future rewards. Our fairness constraint requires that an algorithm never prefers one action over another if the long
-term (discounted) reward of choosing the latter action is higher. Our first result is negative: despite the fact that fairness is consistent with the optimal policy, any learning algorithm satisfying fairness must take time exponential in the number of states to achieve non-trivial approximation to the optimal policy. We then provide a provably fair polynomial time algorithm under an approximate notion of fairness, thus establishing an exponential gap between exact and approximate fairness
الأسئلة المقترحة
سجل دخول لتتمكن من نشر تعليقات
التعليقات
جاري جلب التعليقات
سجل دخول لتتمكن من متابعة معايير البحث التي قمت باختيارها
