Adversarial training approach for local data debiasing

The widespread use of automated decision processes in many areas of our society raises serious ethical issues concerning the fairness of the process and the possible resulting discriminations. In this work, we propose a novel approach called GANsan whose objective is to prevent the possibility of any discrimination i.e., direct and indirect) based on a sensitive attribute by removing the attribute itself as well as the existing correlations with the remaining attributes. Our sanitization algorithm GANsan is partially inspired by the powerful framework of generative adversarial networks (in particular the Cycle-GANs), which offers a flexible way to learn a distribution empirically or to translate between two different distributions. In contrast to prior work, one of the strengths of our approach is that the sanitization is performed in the same space as the original data by only modifying the other attributes as little as possible and thus preserving the interpretability of the sanitized data. As a consequence, once the sanitizer is trained, it can be applied to new data, such as for instance, locally by an individual on his profile before releasing it. Finally, experiments on a real dataset demonstrate the effectiveness of the proposed approach as well as the achievable trade-off between fairness and utility.

[1]  M. Kearns,et al.  Fairness in Criminal Justice Risk Assessments: The State of the Art , 2017, Sociological Methods & Research.

[2]  Suresh Venkatasubramanian,et al.  A comparative study of fairness-enhancing interventions in machine learning , 2018, FAT.

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

[4]  Max Welling,et al.  Auto-Encoding Variational Bayes , 2013, ICLR.

[5]  Corinna Cortes,et al.  Support-Vector Networks , 1995, Machine Learning.

[6]  Krishna P. Gummadi,et al.  Fairness Constraints: Mechanisms for Fair Classification , 2015, AISTATS.

[7]  Max Welling,et al.  The Variational Fair Autoencoder , 2015, ICLR.

[8]  Nikos E. Mastorakis,et al.  Multilayer perceptron and neural networks , 2009 .

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

[10]  Wenliang Du,et al.  Using randomized response techniques for privacy-preserving data mining , 2003, KDD '03.

[11]  Andrew D. Selbst,et al.  Big Data's Disparate Impact , 2016 .

[12]  Julia Rubin,et al.  Fairness Definitions Explained , 2018, 2018 IEEE/ACM International Workshop on Software Fairness (FairWare).

[13]  Yoshua Bengio,et al.  Generative Adversarial Nets , 2014, NIPS.

[14]  Simon Osindero,et al.  Conditional Generative Adversarial Nets , 2014, ArXiv.

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

[16]  Toon Calders,et al.  Discrimination Aware Decision Tree Learning , 2010, 2010 IEEE International Conference on Data Mining.

[17]  Lu Zhang,et al.  FairGAN: Fairness-aware Generative Adversarial Networks , 2018, 2018 IEEE International Conference on Big Data (Big Data).

[18]  Ye Wang,et al.  Privacy-Preserving Adversarial Networks , 2017, 2019 57th Annual Allerton Conference on Communication, Control, and Computing (Allerton).

[19]  P. Dirac Principles of Quantum Mechanics , 1982 .

[20]  J. Friedman Stochastic gradient boosting , 2002 .

[21]  Seth Neel,et al.  Preventing Fairness Gerrymandering: Auditing and Learning for Subgroup Fairness , 2017, ICML.

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

[23]  S L Warner,et al.  Randomized response: a survey technique for eliminating evasive answer bias. , 1965, Journal of the American Statistical Association.

[24]  Cheng Soon Ong,et al.  Costs and Benefits of Fair Representation Learning , 2019, AIES.

[25]  Avi Feller,et al.  Algorithmic Decision Making and the Cost of Fairness , 2017, KDD.

[26]  Jun Sakuma,et al.  Fairness-Aware Classifier with Prejudice Remover Regularizer , 2012, ECML/PKDD.

[27]  Aaron Roth,et al.  Fairness in Learning: Classic and Contextual Bandits , 2016, NIPS.

[28]  Chris Piech,et al.  Achieving Fairness through Adversarial Learning: an Application to Recidivism Prediction , 2018, ArXiv.

[29]  M. Mahmoud,et al.  Expert System for Banking Credit Decision , 2008, 2008 International Conference on Computer Science and Information Technology.

[30]  Catuscia Palamidessi,et al.  Generating Optimal Privacy-Protection Mechanisms via Machine Learning , 2019, ArXiv.

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

[32]  Carlos Eduardo Scheidegger,et al.  Certifying and Removing Disparate Impact , 2014, KDD.

[33]  Kush R. Varshney,et al.  Fairness GAN , 2018, IBM J. Res. Dev..

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

[35]  Ninghui Li,et al.  t-Closeness: Privacy Beyond k-Anonymity and l-Diversity , 2007, 2007 IEEE 23rd International Conference on Data Engineering.

[36]  Yoshua Bengio,et al.  Learning Anonymized Representations with Adversarial Neural Networks , 2018, ArXiv.

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

[38]  Toniann Pitassi,et al.  Fairness through awareness , 2011, ITCS '12.

[39]  Ayan Chakrabarti,et al.  Learning Privacy Preserving Encodings Through Adversarial Training , 2018, 2019 IEEE Winter Conference on Applications of Computer Vision (WACV).

[40]  Xintao Wu,et al.  Using Randomized Response for Differential Privacy Preserving Data Collection , 2016, EDBT/ICDT Workshops.

[41]  Toon Calders,et al.  Classifying without discriminating , 2009, 2009 2nd International Conference on Computer, Control and Communication.

[42]  Bernhard Schölkopf,et al.  A Kernel Method for the Two-Sample-Problem , 2006, NIPS.

[43]  Giannis Tzimas,et al.  An Integrated E-Recruitment System for Automated Personality Mining and Applicant Ranking , 2012, Internet Res..