iFlipper: Label Flipping for Individual Fairness
Hantian Zhang, Ki Hyun Tae, Jaeyoung Park, Xu Chu, Steven Euijong, Whang

TL;DR
iFlipper is a pre-processing method that optimally flips labels to improve individual fairness in machine learning, balancing fairness violations and accuracy, and can be combined with other fairness techniques.
Contribution
This paper introduces iFlipper, a novel label flipping approach with theoretical guarantees for enhancing individual fairness before training.
Findings
iFlipper outperforms baseline methods in fairness and accuracy
The label flipping problem is NP-hard, but approximable with linear programming
Combining iFlipper with in-processing methods yields better results
Abstract
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…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsMachine Learning and Data Classification · Explainable Artificial Intelligence (XAI) · Adversarial Robustness in Machine Learning
MethodsTest
