Probabilistic Verification of Neural Networks Against Group Fairness

by   Bing Sun, et al.

Fairness is crucial for neural networks which are used in applications with important societal implication. Recently, there have been multiple attempts on improving fairness of neural networks, with a focus on fairness testing (e.g., generating individual discriminatory instances) and fairness training (e.g., enhancing fairness through augmented training). In this work, we propose an approach to formally verify neural networks against fairness, with a focus on independence-based fairness such as group fairness. Our method is built upon an approach for learning Markov Chains from a user-provided neural network (i.e., a feed-forward neural network or a recurrent neural network) which is guaranteed to facilitate sound analysis. The learned Markov Chain not only allows us to verify (with Probably Approximate Correctness guarantee) whether the neural network is fair or not, but also facilities sensitivity analysis which helps to understand why fairness is violated. We demonstrate that with our analysis results, the neural weights can be optimized to improve fairness. Our approach has been evaluated with multiple models trained on benchmark datasets and the experiment results show that our approach is effective and efficient.



There are no comments yet.


page 1

page 2

page 3

page 4


Perfectly Parallel Fairness Certification of Neural Networks

Recently, there is growing concern that machine-learning models, which c...

Fair Representation: Guaranteeing Approximate Multiple Group Fairness for Unknown Tasks

Motivated by scenarios where data is used for diverse prediction tasks, ...

NeuronFair: Interpretable White-Box Fairness Testing through Biased Neuron Identification

Deep neural networks (DNNs) have demonstrated their outperformance in va...

SOCRATES: Towards a Unified Platform for Neural Network Verification

Studies show that neural networks, not unlike traditional programs, are ...

Provably Training Neural Network Classifiers under Fairness Constraints

Training a classifier under fairness constraints has gotten increasing a...

Gradient Reversal Against Discrimination

No methods currently exist for making arbitrary neural networks fair. In...

Verifying Fairness Properties via Concentration

As machine learning systems are increasingly used to make real world leg...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.