An Overview on the Use of Adversarial Learning Strategies to Ensure Fairness on Machine Learning Models


Context: The information age brought wide data availability, which allowed technological advances, especially when looking at machine learning (ML) algorithms that have achieved significant results for the most diverse tasks. Thus, information systems are now implementing and incorporating these algorithms, including in critical areas. Problem: Given this widespread use and already observed examples of misuse of its decisions, it is essential to consider the harm and social impacts that ML models can bring for society, for example, biased and discriminatory decisions coming from biased data or programmers. Solution: This article provides an overview of an eminent area of study on the use of adversarial learning to encode fairness constraints in ML models. IS Theory: This work is related to socio-technical theory since we consider one of the so-called socio-algorithmic problems, algorithmic discrimination. We consider a specific set of approaches to encoding fair behaviors. Method: We selected and analyzed the literature works on the use of adversarial learning for encoding fairness, aiming to answer defined research questions. Summary of Results: As main results, this work presents answers to the following research questions: What is the type of their approach? What fairness constraints did they encode into their models? What evaluation metrics did they use to assess their proposals? What datasets did they use? Contributions and Impact in the IS area: We expect to assist future research in the fairness area. Thus the article's main contribution is to provide a reference for the community, summarizing the main topics about the adversarial learning approaches for achieving fairness.
Palavras-chave: adversarial learning, bias, fairness


Julia Angwin, Jeff Larson, Surya Mattu, and Lauren Kirchner. 2016. Machine bias: There's software used across the country to predict future criminals. And it's biased against blacks. [link].

Richard Berk, Hoda Heidari, Shahin Jabbari, Michael Kearns, and Aaron Roth. 2018. Fairness in criminal justice risk assessments: The state of the art. Sociological Methods & Research(2018). 

Alex Beutel, Jilin Chen, Zhe Zhao, and Ed H Chi. 2017. Data decisions and theoretical implications when adversarially learning fair representations. arXiv preprint arXiv:1707.00075(2017). 

Tolga Bolukbasi, Kai-Wei Chang, James Y Zou, Venkatesh Saligrama, and Adam T Kalai. 2016. Man is to computer programmer as woman is to homemaker? debiasing word embeddings. In Advances in neural information processing systems. 4349–4357. 

Brasil. 2018. Lei nº13.709, de 14 de agosto de 2018. Lei Geral de Proteção de Dados Pessoais (LGPD).

Carina Brito. 2020. Sistema de reconhecimento facial erra, e homem negro é preso por engano. [link].

Joy Buolamwini and Timnit Gebru. 2018. Gender shades: Intersectional accuracy disparities in commercial gender classification. In Conference on fairness, accountability and transparency. PMLR, 77–91. 

Toon Calders, Faisal Kamiran, and Mykola Pechenizkiy. 2009. Building classifiers with independency constraints. In 2009 IEEE International Conference on Data Mining Workshops. IEEE, 13–18. 

European Council. 2016. EU General Data Protection Regulation (GDPR) 2016/679.

Thomas M Cover and Joy A Thomas. 2012. Elements of information theory. John Wiley & Sons. 

Kimberlé Crenshaw. 1989. Demarginalizing the intersection of race and sex: A black feminist critique of antidiscrimination doctrine, feminist theory and antiracist politics. u. Chi. Legal f. (1989), 139. 

Paula Regina Dal'Evedove and Mariângela Spotti Lopes Fujita. 2009. A abordagem sociológica em Ciência da Informação: um novo olhar investigativo. A ciência da informação criadora de conhecimento 2 (2009), 147–156. 

Filip Karlo Došilović, Mario Brčić, and Nikica Hlupić. 2018. Explainable artificial intelligence: A survey. In 2018 41st International convention on information and communication technology, electronics and microelectronics (MIPRO). IEEE, 0210–0215. 

Cynthia Dwork, Moritz Hardt, Toniann Pitassi, Omer Reingold, and Richard Zemel. 2012. Fairness through awareness. In Proceedings of the 3rd innovations in theoretical computer science conference. 214–226. 

Ian Goodfellow, Jean Pouget-Abadie, Mehdi Mirza, Bing Xu, David Warde-Farley, Sherjil Ozair, Aaron Courville, and Yoshua Bengio. 2014. Generative adversarial nets. In Advances in neural information processing systems. 2672–2680. 

Odd Erik Gundersen, Yolanda Gil, and David W. Aha. 2018. On Reproducible AI: Towards Reproducible Research, Open Science, and Digital Scholarship in AI Publications. AI Magazine 39, 3 (Sep. 2018), 56–68.

Benjamin Haibe-Kains, George Alexandru Adam, Ahmed Hosny, Farnoosh Khodakarami, Levi Waldron, Bo Wang, Chris McIntosh, Anna Goldenberg, Anshul Kundaje, Casey S Greene, et al. 2020. Transparency and reproducibility in artificial intelligence. Nature 586, 7829 (2020), E14–E16. 

Moritz Hardt, Eric Price, and Nati Srebro. 2016. Equality of opportunity in supervised learning. In Advances in neural information processing systems. 3315–3323. 

Gareth P Jones, James M Hickey, Pietro G Di Stefano, Charanpal Dhajgal, Laura C Stoddart, and Vlasios Vasileiou. 2020. Metrics and methods for a systematic comparison of fairness-aware machine learning algorithms. arXiv preprint arXiv:2010.03986(2020). 

Michael Kearns and Aaron Roth. 2019. The ethical algorithm: The science of socially aware algorithm design. Oxford University Press. 

Luiz Lima, Danielle Ricarte, and Clauirton Siebra. 2021. Assessing Fair Machine Learning Strategies Through a Fairness-Utility Trade-off Metric. In Anais do XVIII Encontro Nacional de Inteligência Artificial e Computacional (Evento Online). SBC, Porto Alegre, RS, Brasil, 607–618.

Kristian Lum and James Johndrow. 2016. A statistical framework for fair predictive algorithms. arXiv preprint arXiv:1610.08077(2016). 

David Madras, Elliot Creager, Toniann Pitassi, and Richard Zemel. 2018. Learning Adversarially Fair and Transferable Representations. In Proceedings of the 35th International Conference on Machine Learning. 3384–3393.

Ninareh Mehrabi, Fred Morstatter, Nripsuta Saxena, Kristina Lerman, and Aram Galstyan. 2019. A survey on bias and fairness in machine learning. arXiv preprint arXiv:1908.09635(2019). 

Ziad Obermeyer, Brian Powers, Christine Vogeli, and Sendhil Mullainathan. 2019. Dissecting racial bias in an algorithm used to manage the health of populations. Science 366, 6464 (2019), 447–453. 

Augustus Odena, Christopher Olah, and Jonathon Shlens. 2017. Conditional image synthesis with auxiliary classifier gans. In Proceedings of the 34th International Conference on Machine Learning-Volume 70. JMLR. org, 2642–2651. 

Lívia Ruback, Sandra Avila, and Lucia Cantero. 2021. Vieses no Aprendizado de Máquina e suas Implicações Sociais: Um Estudo de Caso no Reconhecimento Facial. In Anais do II Workshop sobre as Implicações da Computação na Sociedade (Evento Online). SBC, Porto Alegre, RS, Brasil, 90–101.

Stuart Russell and Peter Norvig. 2009. Artificial intelligence: a modern approach. Prentice Hall. 

Sahil Verma and Julia Rubin. 2018. Fairness definitions explained. In 2018 IEEE/ACM International Workshop on Software Fairness (FairWare). IEEE, 1–7. 

Depeng Xu, Shuhan Yuan, Lu Zhang, and Xintao Wu. 2018. Fairgan: Fairness-aware generative adversarial networks. In IEEE International Conference on Big Data (Big Data). IEEE, 570–575. 

Depeng Xu, Shuhan Yuan, Lu Zhang, and Xintao Wu. 2019. FairGAN+: Achieving Fair Data Generation and Classification through Generative Adversarial Nets. In IEEE International Conference on Big Data (Big Data). IEEE, 1401–1406. 

Brian Hu Zhang, Blake Lemoine, and Margaret Mitchell. 2018. Mitigating unwanted biases with adversarial learning. In Proceedings of the 2018 AAAI/ACM Conference on AI, Ethics, and Society. 335–340. 
Como Citar

Selecione um Formato
LIMA, Luiz Fernando Fonsêca Pinheiro de; RICARTE, Danielle Rousy Dias; SIEBRA, Clauirton de Albuquerque. An Overview on the Use of Adversarial Learning Strategies to Ensure Fairness on Machine Learning Models. In: SIMPÓSIO BRASILEIRO DE SISTEMAS DE INFORMAÇÃO (SBSI), 18. , 2022, Curitiba. Anais [...]. Porto Alegre: Sociedade Brasileira de Computação, 2022 .