Equal Opportunity of Coverage in Fair Regression

Authors: Fangxin Wang, Lu Cheng, Ruocheng Guo, Kay Liu, Philip S Yu

NeurIPS 2023 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Experimental results demonstrate the effectiveness of our method in improving EOC.
Researcher Affiliation Collaboration Fangxin Wang University of Illinois Chicago Chicago, USA fwang51@uic.edu Lu Cheng University of Illinois Chicago Chicago, USA lucheng@uic.edu Ruocheng Guo Byte Dance Research London, UK rguo.asu@gmail.com Kay Liu University of Illinois Chicago Chicago, USA zliu234@uic.edu Philip S. Yu University of Illinois Chicago Chicago, USA psyu@uic.edu
Pseudocode Yes To address this issue, we propose Binned Fair Quantile Regression (BFQR) (see Algorithm 1 in Appendix 8.2.1).
Open Source Code Yes Our code is publicly available at https://github.com/fangxin-wang/bfqr.
Open Datasets Yes We further evaluate our method on two benchmark datasets: Adult [44, 45] where gender is the protected attribute and the outcome is salary; MEPS (Medical Expenditure Panel Survey) data [46, 11] where race is the protected attribute and the outcome is the health care system utilization score.
Dataset Splits Yes Every experiment is repeated 100 times on random divisions of data with different seeds, with |Dtr| : |Dc| : |Dt| = 3 : 1 : 1.
Hardware Specification No The paper does not explicitly describe the specific hardware used to run its experiments, such as CPU or GPU models, or cloud computing instances with detailed specifications.
Software Dependencies No The paper mentions using a 'QR model' as the base for conformal prediction methods but does not provide specific software names with version numbers for reproducibility (e.g., 'PyTorch 1.9', 'scikit-learn 1.0').
Experiment Setup Yes The base model for all compared conformal prediction methods is set as the QR model at the level of 0.05 and 0.95, and the desired marginal coverage is set to 0.9.