inFairness#

Intuitively, an individually fair Machine Learning (ML) model treats similar inputs similarly. Formally, the leading notion of individual fairness is metric fairness (Dwork et al., 2011); it requires:

d_{y} (h (x_{1}), h (x_{2})) \leq L d_{x} (x_{1}, x_{2}) \forall x_{1}, x_{2} \in X

Here, $h : X \to Y$ is a ML model, where $X$ and $Y$ are input and output spaces; $d_{x}$ and $d_{y}$ are metrics on the input and output spaces, and $L \geq 0$ is a Lipchitz constant. This constrained optimization equation states that the distance between the model predictions for inputs $x_{1}$ and $x_{2}$ is upper-bounded by the fair distance between the inputs $x_{1}$ and $x_{2}$ . Here, the fair metric $d_{x}$ encodes our intuition of which samples should be treated similarly by the ML model, and in designing so, we ensure that for input samples considered similar by the fair metric $d_{x}$ , the model outputs will be similar as well.

inFairness is a PyTorch package that supports auditing, training, and post-processing ML models for individual fairness. At its core, the library implements the key components of individual fairness pipeline: $d_{x}$ - distance in the input space, $d_{y}$ - distance in the output space, and the learning algorithms to optimize for the equation above.

For an in-depth tutorial of Individual Fairness and the inFairness package, please watch this tutorial. Also, take a look at the examples folder for illustrative use-cases.

Installation#

inFairness can be installed using pip:

pip install inFairness

Alternatively, if you wish to install the latest development version, you can install directly by cloning the code repository from the GitHub repo:

git clone https://github.com/IBM/inFairness
cd inFairness
pip install -e .

Features#

inFairness currently supports:

Training of individually fair models : [Docs]
Auditing pre-trained ML models for individual fairness : [Docs]
Post-processing for Individual Fairness : [Docs]

The package implements the following components:

Algorithms#

Sensitive Set Invariance (SenSeI): [Paper], [Docs]
Sensitive Subspace Robustness (SenSR): [Paper], [Docs]

Auditors#

Sensitive Set Invariance (SenSeI) Auditor: [Paper], [Docs]
Sensitive Subspace Robustness (SenSR) Auditor: [Paper], [Docs]

Metrics#

Embedded Xenial Pair Logistic Regression Metric (EXPLORE): [Paper], [Docs]
SVD Sensitive Subspace Metric: [Paper], [Docs]

Post-Processing algorithms#

Graph Laplacian Individual Fairness (GLIF): [Paper], [Docs]

API Documentation#

Index

Package Reference