On Learning Fairness and Accuracy on Multiple Subgroups

Authors: Changjian Shui, Gezheng Xu, Qi CHEN, Jiaqi Li, Charles X. Ling, Tal Arbel, Boyu Wang, Christian Gagné

NeurIPS 2022 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental We evaluate the proposed framework on real-world datasets. Empirical evidence suggests the consistently improved fair predictions, as well as the comparable accuracy to the baselines.
Researcher Affiliation Academia 1Centre for Intelligent Machines, Mc Gill University 2Mila, Quebec AI Institute 3Department of Computer Science, University of Western Ontario 4Institute Intelligence and Data, Université Laval 5CIFAR AI Chair
Pseudocode Yes Algorithm 1 Fair and Informative Learning for Multiple Subgroups (FAMS)
Open Source Code Yes Code is available at https://github.com/xugezheng/FAMS.
Open Datasets Yes We adopt Amazon review dataset [55, 40]... We also use the toxic comment dataset [58]...
Dataset Splits Yes We draw and then fix 200 users from the original dataset, which includes the training, validation, and test sets.
Hardware Specification No The paper does not specify the hardware used for experiments, such as specific GPU models, CPU types, or memory.
Software Dependencies No The paper mentions using "Distil BERT [57]" but does not provide specific version numbers for it or any other software dependencies like programming languages or libraries.
Experiment Setup No In the implementation, we first adopt Distil BERT [57] to learn the embedding with dimension R768. Then we adopt fw and fwa as the four-layer fully connected neural network... Additional experimental details are delegated to the Appendix.