Fairness GAN

In this paper, we introduce the Fairness GAN, an approach for generating a dataset that is plausibly similar to a given multimedia dataset, but is more fair with respect to protected attributes in allocative decision making. We propose a novel auxiliary classifier GAN that strives for demographic parity or equality of opportunity and show empirical results on several datasets, including the CelebFaces Attributes (CelebA) dataset, the Quick, Draw!\ dataset, and a dataset of soccer player images and the offenses they were called for. The proposed formulation is well-suited to absorbing unlabeled data; we leverage this to augment the soccer dataset with the much larger CelebA dataset. The methodology tends to improve demographic parity and equality of opportunity while generating plausible images.

[1]  Alexandra Chouldechova,et al.  Does mitigating ML's impact disparity require treatment disparity? , 2017, NeurIPS.

[2]  John Langford,et al.  A Reductions Approach to Fair Classification , 2018, ICML.

[3]  Aaron C. Courville,et al.  Improved Training of Wasserstein GANs , 2017, NIPS.

[4]  Josep Domingo-Ferrer,et al.  A Methodology for Direct and Indirect Discrimination Prevention in Data Mining , 2013, IEEE Transactions on Knowledge and Data Engineering.

[5]  Ian J. Goodfellow,et al.  NIPS 2016 Tutorial: Generative Adversarial Networks , 2016, ArXiv.

[6]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[7]  Mark D. Shermis,et al.  State-of-the-art automated essay scoring: Competition, results, and future directions from a United States demonstration , 2014 .

[8]  Zhe Zhao,et al.  Data Decisions and Theoretical Implications when Adversarially Learning Fair Representations , 2017, ArXiv.

[9]  Jun Sakuma,et al.  Fairness-aware Learning through Regularization Approach , 2011, 2011 IEEE 11th International Conference on Data Mining Workshops.

[10]  Kush R. Varshney,et al.  Decision Making With Quantized Priors Leads to Discrimination , 2017, Proceedings of the IEEE.

[11]  Toniann Pitassi,et al.  Learning Fair Representations , 2013, ICML.

[12]  Nathan Srebro,et al.  Equality of Opportunity in Supervised Learning , 2016, NIPS.

[13]  Mathew H. Evans,et al.  Many Analysts, One Data Set: Making Transparent How Variations in Analytic Choices Affect Results , 2018, Advances in Methods and Practices in Psychological Science.

[14]  Yee Whye Teh,et al.  The Concrete Distribution: A Continuous Relaxation of Discrete Random Variables , 2016, ICLR.

[15]  Jonathon Shlens,et al.  Conditional Image Synthesis with Auxiliary Classifier GANs , 2016, ICML.

[16]  Bogdan Raducanu,et al.  Invertible Conditional GANs for image editing , 2016, ArXiv.

[17]  Yotam Shmargad,et al.  How Algorithms Discriminate Based on Data They Lack: Challenges, Solutions, and Policy Implications , 2018, Journal of Information Policy.

[18]  Kush R. Varshney,et al.  Optimized Pre-Processing for Discrimination Prevention , 2017, NIPS.

[19]  Blake Lemoine,et al.  Mitigating Unwanted Biases with Adversarial Learning , 2018, AIES.

[20]  Salvatore Ruggieri,et al.  Using t-closeness anonymity to control for non-discrimination , 2015, Trans. Data Priv..

[21]  Kush R. Varshney,et al.  An End-To-End Machine Learning Pipeline That Ensures Fairness Policies , 2017, ArXiv.

[22]  Ben Poole,et al.  Categorical Reparameterization with Gumbel-Softmax , 2016, ICLR.

[23]  Takeru Miyato,et al.  cGANs with Projection Discriminator , 2018, ICLR.

[24]  拓海 杉山,et al.  “Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks”の学習報告 , 2017 .

[25]  Jonathon Shlens,et al.  A Learned Representation For Artistic Style , 2016, ICLR.

[26]  Xiaogang Wang,et al.  Deep Learning Face Attributes in the Wild , 2014, 2015 IEEE International Conference on Computer Vision (ICCV).

[27]  Krishna P. Gummadi,et al.  Fairness Beyond Disparate Treatment & Disparate Impact: Learning Classification without Disparate Mistreatment , 2016, WWW.

[28]  Benjamin Fish,et al.  A Confidence-Based Approach for Balancing Fairness and Accuracy , 2016, SDM.

[29]  Gilles Louppe,et al.  Learning to Pivot with Adversarial Networks , 2016, NIPS.

[30]  Yuichi Yoshida,et al.  Spectral Normalization for Generative Adversarial Networks , 2018, ICLR.

[31]  Sara Hajian,et al.  Simultaneous Discrimination Prevention and Privacy Protection in Data Publishing and Mining , 2013, ArXiv.

[32]  M. Turk,et al.  Eigenfaces for Recognition , 1991, Journal of Cognitive Neuroscience.

[33]  Chi-Keung Tang,et al.  Conditional CycleGAN for Attribute Guided Face Image Generation , 2017, ArXiv.

[34]  Jae Hyun Lim,et al.  Geometric GAN , 2017, ArXiv.

[35]  Varun Chandola,et al.  Server, server in the cloud. Who is the fairest in the crowd? , 2017, ArXiv.

[36]  Amos J. Storkey,et al.  Censoring Representations with an Adversary , 2015, ICLR.

[37]  Krishna P. Gummadi,et al.  From Parity to Preference-based Notions of Fairness in Classification , 2017, NIPS.

[38]  Jon M. Kleinberg,et al.  Inherent Trade-Offs in the Fair Determination of Risk Scores , 2016, ITCS.

[39]  Toon Calders,et al.  Data preprocessing techniques for classification without discrimination , 2011, Knowledge and Information Systems.

[40]  Toniann Pitassi,et al.  Learning Adversarially Fair and Transferable Representations , 2018, ICML.

[41]  Les Perelman,et al.  When “the state of the art” is counting words , 2014 .