SoFaiR: Single Shot Fair Representation Learning

Authors: Xavier Gitiaux, Huzefa Rangwala

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

Reproducibility Variable Result LLM Response
Research Type Experimental Empirically, we find on three datasets that So Fai R achieves similar fairness-information tradeoffs as its multi-shot counterparts.
Researcher Affiliation Academia Xavier Gitiaux and Huzefa Rangwala George Mason University {xgitiaux, rangwala}@gmu.edu
Pseudocode No The paper does not contain any structured pseudocode or algorithm blocks.
Open Source Code Yes The code publicly available here2. 2See https://github.com/Gitiauxx/So Fai R
Open Datasets Yes We validate our single-shot approach with three benchmark datasets: DSprite-Unfair, Adults and Heritage.
Dataset Splits No The paper mentions training and testing but does not explicitly provide specific details about validation dataset splits (e.g., percentages, sample counts) in the main text.
Hardware Specification Yes We perform the experiment on a AMD Ryzen Threadripper 2950X 16-Core Processor CPU and a NVIDIA GV102 GPU.
Software Dependencies No The paper does not provide specific version numbers for software dependencies used in the experiments (e.g., Python, PyTorch, TensorFlow versions).
Experiment Setup No Architecture details and hyperparameter values are in the supplementary file.