اشترك بالحزمة الذهبية واحصل على وصول غير محدود شمرا أكاديميا
تسجيل مستخدم جديدWhat is Fair? Exploring Pareto-Efficiency for Fairness Constrained Classifiers
69
0
0.0
(
0
)
اسأل ChatGPT حول البحث
ﻻ يوجد ملخص باللغة العربية
The potential for learned models to amplify existing societal biases has been broadly recognized. Fairness-aware classifier constraints, which apply equality metrics of performance across subgroups defined on sensitive attributes such as race and gender, seek to rectify inequity but can yield non-uniform degradation in performance for skewed datasets. In certain domains, imbalanced degradation of performance can yield another form of unintentional bias. In the spirit of constructing fairness-aware algorithms as societal imperative, we explore an alternative: Pareto-Efficient Fairness (PEF). Theoretically, we prove that PEF identifies the operating point on the Pareto curve of subgroup performances closest to the fairness hyperplane, maximizing multiple subgroup accuracy. Empirically we demonstrate that PEF outperforms by achieving Pareto levels in accuracy for all subgroups compared to strict fairness constraints in several UCI datasets.
قيم البحث
اقرأ أيضاً
Common fairness definitions in machine learning focus on balancing notions of disparity and utility. In this work, we study fairness in the context of risk disparity among sub-populations. We are interested in learning models that minimize performanc
e discrepancies across sensitive groups without causing unnecessary harm. This is relevant to high-stakes domains such as healthcare, where non-maleficence is a core principle. We formalize this objective using Pareto frontiers, and provide analysis, based on recent works in fairness, to exemplify scenarios were perfect fairness might not be feasible without doing unnecessary harm. We present a methodology for training neural networks that achieve our goal by dynamically re-balancing subgroups risks. We argue that even in domains where fairness at cost is required, finding a non-unnecessary-harm fairness model is the optimal initial step. We demonstrate this methodology on real case-studies of predicting ICU patient mortality, and classifying skin lesions from dermatoscopic images.
We revisit the notion of individual fairness proposed by Dwork et al. A central challenge in operationalizing their approach is the difficulty in eliciting a human specification of a similarity metric. In this paper, we propose an operationalization
of individual fairness that does not rely on a human specification of a distance metric. Instead, we propose novel approaches to elicit and leverage side-information on equally deserving individuals to counter subordination between social groups. We model this knowledge as a fairness graph, and learn a unified Pairwise Fair Representation (PFR) of the data that captures both data-driven similarity between individuals and the pairwise side-information in fairness graph. We elicit fairness judgments from a variety of sources, including human judgments for two real-world datasets on recidivism prediction (COMPAS) and violent neighborhood prediction (Crime & Communities). Our experiments show that the PFR model for operationalizing individual fairness is practically viable.
Rankings of people and items has been highly used in selection-making, match-making, and recommendation algorithms that have been deployed on ranging of platforms from employment websites to searching tools. The ranking position of a candidate affect
s the amount of opportunities received by the ranked candidate. It has been observed in several works that the ranking of candidates based on their score can be biased for candidates belonging to the minority community. In recent works, the fairness-aware representative ranking was proposed for computing fairness-aware re-ranking of results. The proposed algorithm achieves the desired distribution of top-ranked results with respect to one or more protected attributes. In this work, we highlight the bias in fairness-aware representative ranking for an individual as well as for a group if the group is sub-active on the platform. We define individual unfairness and group unfairness and propose methods to generate ideal individual and group fair representative ranking if the universal representation ratio is known or unknown. The simulation results show the quantified analysis of fairness in the proposed solutions. The paper is concluded with open challenges and further directions.
Standard approaches to group-based notions of fairness, such as emph{parity} and emph{equalized odds}, try to equalize absolute measures of performance across known groups (based on race, gender, etc.). Consequently, a group that is inherently harder
to classify may hold back the performance on other groups; and no guarantees can be provided for unforeseen groups. Instead, we propose a fairness notion whose guarantee, on each group $g$ in a class $mathcal{G}$, is relative to the performance of the best classifier on $g$. We apply this notion to broad classes of groups, in particular, where (a) $mathcal{G}$ consists of all possible groups (subsets) in the data, and (b) $mathcal{G}$ is more streamlined. For the first setting, which is akin to groups being completely unknown, we devise the {sc PF} (Proportional Fairness) classifier, which guarantees, on any possible group $g$, an accuracy that is proportional to that of the optimal classifier for $g$, scaled by the relative size of $g$ in the data set. Due to including all possible groups, some of which could be too complex to be relevant, the worst-case theoretical guarantees here have to be proportionally weaker for smaller subsets. For the second setting, we devise the {sc BeFair} (Best-effort Fair) framework which seeks an accuracy, on every $g in mathcal{G}$, which approximates that of the optimal classifier on $g$, independent of the size of $g$. Aiming for such a guarantee results in a non-convex problem, and we design novel techniques to get around this difficulty when $mathcal{G}$ is the set of linear hypotheses. We test our algorithms on real-world data sets, and present interesting comparative insights on their performance.
In naturalistic learning problems, a models input contains a wide range of features, some useful for the task at hand, and others not. Of the useful features, which ones does the model use? Of the task-irrelevant features, which ones does the model r
epresent? Answers to these questions are important for understanding the basis of models decisions, as well as for building models that learn versatile, adaptable representations useful beyond the original training task. We study these questions using synthetic datasets in which the task-relevance of input features can be controlled directly. We find that when two features redundantly predict the labels, the model preferentially represents one, and its preference reflects what was most linearly decodable from the untrained model. Over training, task-relevant features are enhanced, and task-irrelevant features are partially suppressed. Interestingly, in some cases, an easier, weakly predictive feature can suppress a more strongly predictive, but more difficult one. Additionally, models trained to recognize both easy and hard features learn representations most similar to models that use only the easy feature. Further, easy features lead to more consistent representations across model runs than do hard features. Finally, models have greater representational similarity to an untrained model than to models trained on a different task. Our results highlight the complex processes that determine which features a model represents.
الأسئلة المقترحة
سجل دخول لتتمكن من نشر تعليقات
التعليقات
جاري جلب التعليقات
سجل دخول لتتمكن من متابعة معايير البحث التي قمت باختيارها
