Fairneuron: Improving Deep Neural Network Fairness with Adversary Games on Selective Neurons

Xuanqi Gao, Juan Zhai, Shiqing Ma, Chao Shen, Yufei Chen, Qian Wang

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

With Deep Neural Network (DNN) being integrated into a growing number of critical systems with far-reaching impacts on society, there are increasing concerns on their ethical performance, such as fairness. Unfortunately, model fairness and accuracy in many cases are contradictory goals to optimize during model training. To solve this issue, there has been a number of works trying to improve model fairness by formalizing an adversarial game in the model level. This approach introduces an adversary that evaluates the fairness of a model besides its prediction accuracy on the main task, and performs joint-optimization to achieve a balanced result. In this paper, we noticed that when performing backward prop-agation based training, such contradictory phenomenon are also observable on individual neuron level. Based on this observation, we propose Fairneuron, a Dnn model automatic repairing tool, to mitigate fairness concerns and balance the accuracy-fairness trade-off without introducing another model. It works on detecting neurons with contradictory optimization directions from accuracy and fairness training goals, and achieving a trade-off by selective dropout. Comparing with state-of-the-art methods, our approach is lightweight, scaling to large models and more efficient. Our eval-uation on three datasets shows that Fairneuron can effectively improve all models' fairness while maintaining a stable utility.

Original languageEnglish (US)
Title of host publicationProceedings - 2022 ACM/IEEE 44th International Conference on Software Engineering, ICSE 2022
PublisherIEEE Computer Society
Pages921-933
Number of pages13
ISBN (Electronic)9781450392211
DOIs
StatePublished - 2022
Event44th ACM/IEEE International Conference on Software Engineering, ICSE 2022 - Pittsburgh, United States
Duration: May 22 2022May 27 2022

Publication series

NameProceedings - International Conference on Software Engineering
Volume2022-May
ISSN (Print)0270-5257

Conference

Conference44th ACM/IEEE International Conference on Software Engineering, ICSE 2022
Country/TerritoryUnited States
CityPittsburgh
Period5/22/225/27/22

All Science Journal Classification (ASJC) codes

  • Software

Keywords

  • fairness
  • neural networks
  • path analysis

Fingerprint

Dive into the research topics of 'Fairneuron: Improving Deep Neural Network Fairness with Adversary Games on Selective Neurons'. Together they form a unique fingerprint.

Cite this