Fairness
1185 papers with code • 3 benchmarks • 20 datasets
Benchmarks
These leaderboards are used to track progress in Fairness
| Trend | Dataset | Best Model | Paper | Code | Compare |
|---|---|---|---|---|---|
|
|||||
|
|||||
|
Libraries
Use these libraries to find Fairness models and implementations
Netflix Prize
UTKFace
MORPH
FairFace
WinoBias
GVGAI
HELP
MIAP
Most implemented papers
FreeMatch: Self-adaptive Thresholding for Semi-supervised Learning
Semi-supervised Learning (SSL) has witnessed great success owing to the impressive performances brought by various methods based on pseudo labeling and consistency regularization.
Fairness Beyond Disparate Treatment & Disparate Impact: Learning Classification without Disparate Mistreatment
To account for and avoid such unfairness, in this paper, we introduce a new notion of unfairness, disparate mistreatment, which is defined in terms of misclassification rates.
Counterfactual Fairness
Machine learning can impact people with legal or ethical consequences when it is used to automate decisions in areas such as insurance, lending, hiring, and predictive policing.
Mitigating Unwanted Biases with Adversarial Learning
giandos200/Zhang-et-al-Mitigating-Unwanted-Biases-with-Adversarial-Learning
•
•
Machine learning is a tool for building models that accurately represent input training data.
A Reductions Approach to Fair Classification
We present a systematic approach for achieving fairness in a binary classification setting.
Delayed Impact of Fair Machine Learning
Fairness in machine learning has predominantly been studied in static classification settings without concern for how decisions change the underlying population over time.
Predicting Race and Ethnicity From the Sequence of Characters in a Name
One way to infer race and ethnicity from names is by relying on the Census Bureau's list of popular last names.
Learning Controllable Fair Representations
Learning data representations that are transferable and are fair with respect to certain protected attributes is crucial to reducing unfair decisions while preserving the utility of the data.
Efficient Task-Specific Data Valuation for Nearest Neighbor Algorithms
The most surprising result is that for unweighted $K$NN classifiers and regressors, the Shapley value of all $N$ data points can be computed, exactly, in $O(N\log N)$ time -- an exponential improvement on computational complexity!
FAT Forensics: A Python Toolbox for Algorithmic Fairness, Accountability and Transparency
Today, artificial intelligence systems driven by machine learning algorithms can be in a position to take important, and sometimes legally binding, decisions about our everyday lives.
