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
FairBatch: Batch Selection for Model Fairness
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
-
Choose Wisely and Privately: Proactive Client Selection for Fair and Efficient Federated Learning
Proposes proactive client selection via differentially private mutual information and Potential Federation Loss optimized by simulated annealing to achieve faster, fairer, and more accurate federated models than unifo...
-
Choose Wisely and Privately: Proactive Client Selection for Fair and Efficient Federated Learning
Proactive client selection in federated learning via differentially private mutual information and simulated annealing to optimize Potential Federation Loss for utility and fairness.
-
CAFP: A Post-Processing Framework for Group Fairness via Counterfactual Model Averaging
CAFP averages a classifier's outputs on each input and its counterfactual with the protected attribute flipped, eliminating direct dependence on the attribute and achieving demographic parity under mild assumptions.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.