SenSeI: Sensitive Set Invariance for Enforcing Individual Fairness

Authors: Mikhail Yurochkin, Yuekai Sun

ICLR 2021 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Finally, in the experimental studies we demonstrate improved fairness metrics in comparison to several recent fair training procedures on three ML tasks that are susceptible to algorithmic bias.
Researcher Affiliation Collaboration Mikhail Yurochkin IBM Research MIT-IBM Watson AI Lab mikhail.yurochkin@ibm.com Yuekai Sun Department of Statistics University of Michigan yuekai@umich.edu
Pseudocode Yes Algorithm 1 Sen Se I: Sensitive Set Invariance
Open Source Code No 3We will open-source the code and merge variable names with their abbreviations
Open Datasets Yes Data is available through the Toxic Comment Classification Challenge Kaggle competition. De-Arteaga et al. (2019) proposed Bias in Bios dataset to study fairness in occupation prediction from a person s bio. The Adult dataset (Bache & Lichman, 2013) is a common benchmark in the group fairness literature.
Dataset Splits Yes We repeat our experiment 10 times with random 70-30 train-test splits, every time utilizing a random subset of 25 counterfactuals during training. We repeat the experiment 10 times with 70-30 train-test splits
Hardware Specification No No specific hardware details (like GPU/CPU models or memory) are provided.
Software Dependencies No The paper mentions BERT but does not provide specific version numbers for any software dependencies or libraries.
Experiment Setup Yes In Table 4 for each hyperparameter we summarize its meaning, abbreviation, name in the code provided with the submission and methods where it is used. To select hyperparameters for each experiment we performed a grid search on an independent train-test split. Then we fixed selected hyperparameters and ran 10 experiment repetitions with random train test splits (these results are reported in the main text). Hyperparameter choices for all experiments are summarized in Tables 5, 6, 7.