REVIEW 3 cited by
FairBatch: Batch Selection for Model Fairness
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
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.
Forward citations
Cited by 3 Pith papers
-
Controllable Feature Whitening for Hyperparameter-Free Bias Mitigation
Controllable Feature Whitening decorrelates target and bias features via a covariance-based whitening transform, reducing spurious-correlation reliance without adversarial training.
-
Risk-averse Fair Multi-class Classification
Systemic coherent risk measures are used to design multi-class classifiers that are robust to label noise and enforce group fairness through a class-risk deviation penalty.
-
Bridging Jensen Gap for Max-Min Group Fairness Optimization in Recommendation
A dual-optimization method for group max-min fairness in recommender systems is proposed to reduce the mini-batch Jensen gap, but the central convergence theorem is internally inconsistent.
Discussion (0). Continue with ORCID to comment.