Adversarial Learned Fair Representations using Dampening and Stacking
Not on the map. Why?
Abstract (arXiv)
As more decisions in our daily life become automated, the need to have machine learning algorithms that make fair decisions increases. In fair representation learning we are tasked with finding a suitable representation of the data in which a sensitive variable is censored. Recent work aims to learn fair representations through adversarial learning. This paper builds upon this work by introducing a novel algorithm which uses dampening and stacking to learn adversarial fair representations. Results show that that our algorithm improves upon earlier work in both censoring and reconstruction.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 12 of its 21 references that are in the map. First posted on arXiv 16 Mar 2022.
Builds on
12 of 21 references.
References · 12
- 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
- 2014Adam: A Method for Stochastic Optimizationcited by 37,240
- 2022Generative Adversarial Networkscited by 5,627
- 2019A Survey on Bias and Fairness in Machine Learningcited by 1,917
- 2018Learning Adversarially Fair and Transferable Representationscited by 353
- 2015The Variational Fair Autoencodercited by 223
- 2015Censoring Representations with an Adversarycited by 192
- 2021Topic Modelling Meets Deep Neural Networks: A Surveycited by 51
- 2019Learning Fair Representations via an Adversarial Frameworkcited by 29
- 2017Stabilizing Adversarial Nets With Prediction Methodscited by 14
- 2021Adversarial Stacked Auto-Encoders for Fair Representation Learningcited by 3
- 2021Using Adversarial Debiasing to Remove Bias from Word Embeddingscited by 2
Built on by
Citing papers per year: 2022: 1.
1 paper.