FairBatch: Batch Selection for Model Fairness

Kangwook Lee, Yuji Roh, Steven Euijong Whang, Changho Suh
2020-12-03

SCID:  54.1/zkjz7x7t
Training a fair machine learning model is essential to prevent demographic disparity. Existing techniques for improving model fairness require broad changes in either data preprocessing or model training, rendering themselves difficult-to-adopt for potentially already complex machine learning systems. We address this problem via the lens of bilevel optimization. While keeping the standard training algorithm as an inner optimizer, we incorporate an outer optimizer so as to equip the inner problem with an additional functionality: Adaptively selecting minibatch sizes for the purpose of improving model fairness. Our batch selection algorithm, which we call FairBatch, implements this optimization and supports prominent fairness measures: equal opportunity, equalized odds, and demographic parity. FairBatch comes with a significant implementation benefit -- it does not require any modification to data preprocessing or model training. For instance, a single-line change of PyTorch code for replacing batch selection part of model training suffices to employ FairBatch. Our experiments conducted both on synthetic and benchmark real data demonstrate that FairBatch can provide such functionalities while achieving comparable (or even greater) performances against the state of the arts. Furthermore, FairBatch can readily improve fairness of any pre-trained model simply via fine-tuning. It is also compatible with existing batch selection techniques intended for different purposes, such as faster convergence, thus gracefully achieving multiple purposes.
Publication Details
Publication Date
2020-12-03
Journal
Publisher
ISSN
Access Type
Author Information
Authors
Kangwook Lee
Yuji Roh
Steven Euijong Whang
Changho Suh
Explore More Research
Use the citation graph to discover related papers and expand your research horizons.
Click any node to explore
Download PDF
100%