iFlipper: Label Flipping for Individual Fairness
As machine learning becomes prevalent, mitigating any unfairness present in the training data becomes critical. Among the various notions of fairness, this paper focuses on the well-known individual fairness, which states that similar individuals should be treated similarly. While individual fairness can be improved when training a model (in-processing), we contend that fixing the data before model training (pre-processing) is a more fundamental solution. In particular, we show that label flipping is an effective pre-processing technique for improving individual fairness. Our system iFlipper solves the optimization problem of minimally flipping labels given a limit to the individual fairness violations, where a violation occurs when two similar examples in the training data have different labels. We first prove that the problem is NP-hard. We then propose an approximate linear programming algorithm and provide theoretical guarantees on how close its result is to the optimal solution in terms of the number of label flips. We also propose techniques for making the linear programming solution more optimal without exceeding the violations limit. Experiments on real datasets show that iFlipper significantly outperforms other pre-processing baselines in terms of individual fairness and accuracy on unseen test sets. In addition, iFlipper can be combined with in-processing techniques for even better results.
Code (1)
Tasks
FairnessMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
EiFFFeL: Enforcing Fairness in Forests by Flipping Leaves
Nowadays Machine Learning (ML) techniques are extensively adopted in many socially sensitive systems, thus requiring to carefully study the fairness of the decisions taken by such systems. Many approaches have been propo…
FairnessCertifying the Fairness of KNN in the Presence of Dataset Bias
We propose a method for certifying the fairness of the classification result of a widely used supervised learning algorithm, the k-nearest neighbors (KNN), under the assumption that the training data may have historical …
FairnessCertified Robustness to Adversarial Label-Flipping Attacks via Randomized Smoothing
This paper considers label-flipping attacks, a type of data poisoning attack where an adversary relabels a small number of examples in a training set in order to degrade the performance of the resulting classifier. In th…
Binary ClassificationData PoisoningApproaching the Harm of Gradient Attacks While Only Flipping Labels
Machine learning systems deployed in distributed or federated environments are highly susceptible to adversarial manipulations, particularly availability attacks -adding imperceptible perturbations to training data, ther…
Data PoisoningThe Price of Diversity
Systemic bias with respect to gender, race and ethnicity, often unconscious, is prevalent in datasets involving choices among individuals. Consequently, society has found it challenging to alleviate bias and achieve dive…
Diversity