FETA: Fairness Enforced Verifying, Training, and Predicting Algorithms for Neural Networks

by   Kiarash Mohammadi, et al.

Algorithmic decision making driven by neural networks has become very prominent in applications that directly affect people's quality of life. In this paper, we study the problem of verifying, training, and guaranteeing individual fairness of neural network models. A popular approach for enforcing fairness is to translate a fairness notion into constraints over the parameters of the model. However, such a translation does not always guarantee fair predictions of the trained neural network model. To address this challenge, we develop a counterexample-guided post-processing technique to provably enforce fairness constraints at prediction time. Contrary to prior work that enforces fairness only on points around test or train data, we are able to enforce and guarantee fairness on all points in the input domain. Additionally, we propose an in-processing technique to use fairness as an inductive bias by iteratively incorporating fairness counterexamples in the learning process. We have implemented these techniques in a tool called FETA. Empirical evaluation on real-world datasets indicates that FETA is not only able to guarantee fairness on-the-fly at prediction time but also is able to train accurate models exhibiting a much higher degree of individual fairness.


page 1

page 2

page 3

page 4


Counterexample-Guided Learning of Monotonic Neural Networks

The widespread adoption of deep learning is often attributed to its auto...

Provable Fairness for Neural Network Models using Formal Verification

Machine learning models are increasingly deployed for critical decision-...

Variance, Self-Consistency, and Arbitrariness in Fair Classification

In fair classification, it is common to train a model, and to compare an...

Post-Hoc Methods for Debiasing Neural Networks

As deep learning models become tasked with more and more decisions that ...

Ensuring Fairness under Prior Probability Shifts

In this paper, we study the problem of fair classification in the presen...

DeepSaDe: Learning Neural Networks that Guarantee Domain Constraint Satisfaction

As machine learning models, specifically neural networks, are becoming i...

Fairify: Fairness Verification of Neural Networks

Fairness of machine learning (ML) software has become a major concern in...

Please sign up or login with your details

Forgot password? Click here to reset