Notice: The reproducibility variables underlying each score are classified using an automated LLM-based pipeline, validated against a manually labeled dataset. LLM-based classification introduces uncertainty and potential bias; scores should be interpreted as estimates. Full accuracy metrics and methodology are described in Coakley et alK. L. Coakley, T. Snelleman, H. Hoos, and O. E. Gundersen, "The embrace of open science: An analysis of a decade of AI research and 56 800 conference papers," Under Review, 2026..
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 | Venue PDF | 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. |