Discovering Fair Representations in the Data Domain

Quadrianto, Novi; Sharmanska, Viktoriia; Thomas, Oliver

doi:10.1109/cvpr.2019.00842

Cited by 99 publications

(90 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this work, we benchmark our model on widely adopted datasets [e.g., , Ricanek and Tesafaye (2006)] that are annotated with binary gender labels. In particular, the datasets are annotated with the sex labels 'Male' and 'Female', and therefore it is common practice in both the face analysis (Ng et al 2012;Dantcheva et al 2015) and fairness literature (Buolamwini and Gebru 2018;Quadrianto et al 2019;Zhao et al 2017;Hendricks et al 2018) to use these available labels under this categorization. As such, we can only address gender bias within this imposed binary classification paradigm.…”

Section: Methodsmentioning

confidence: 99%

“…These methods employ techniques from domain adaptation to learn a representation that minimizes classification loss while being invariant to the sensitive attribute. In the lat-ter category, Sattigeri et al (2018) extend AC-GAN (Odena et al 2017) to generate a fair dataset, while Quadrianto et al (2018) use an autoencoder to remove sensitive information from images. In this work, we introduce an image-to-image translation model to augment the training set, and thus, our framework is most closely related to Quadrianto et al (2018).…”

Section: Fairness-aware Learning and Face Analysismentioning

confidence: 99%

“…In the lat-ter category, Sattigeri et al (2018) extend AC-GAN (Odena et al 2017) to generate a fair dataset, while Quadrianto et al (2018) use an autoencoder to remove sensitive information from images. In this work, we introduce an image-to-image translation model to augment the training set, and thus, our framework is most closely related to Quadrianto et al (2018). However, contrary to Quadrianto et al (2018), our neural style transfer approach is able to generate naturalistic faces by translating demographic attributes instead of removing them (e.g., gender-less faces).…”

Section: Fairness-aware Learning and Face Analysismentioning

confidence: 99%

“…In this work, we introduce an image-to-image translation model to augment the training set, and thus, our framework is most closely related to Quadrianto et al (2018). However, contrary to Quadrianto et al (2018), our neural style transfer approach is able to generate naturalistic faces by translating demographic attributes instead of removing them (e.g., gender-less faces).…”

Section: Fairness-aware Learning and Face Analysismentioning

confidence: 99%

See 3 more Smart Citations

Mitigating Demographic Bias in Facial Datasets with Style-Based Multi-attribute Transfer

et al. 2021

View full text Add to dashboard Cite

Deep learning has catalysed progress in tasks such as face recognition and analysis, leading to a quick integration of technological solutions in multiple layers of our society. While such systems have proven to be accurate by standard evaluation metrics and benchmarks, a surge of work has recently exposed the demographic bias that such algorithms exhibit–highlighting that accuracy does not entail fairness. Clearly, deploying biased systems under real-world settings can have grave consequences for affected populations. Indeed, learning methods are prone to inheriting, or even amplifying the bias present in a training set, manifested by uneven representation across demographic groups. In facial datasets, this particularly relates to attributes such as skin tone, gender, and age. In this work, we address the problem of mitigating bias in facial datasets by data augmentation. We propose a multi-attribute framework that can successfully transfer complex, multi-scale facial patterns even if these belong to underrepresented groups in the training set. This is achieved by relaxing the rigid dependence on a single attribute label, and further introducing a tensor-based mixing structure that captures multiplicative interactions between attributes in a multilinear fashion. We evaluate our method with an extensive set of qualitative and quantitative experiments on several datasets, with rigorous comparisons to state-of-the-art methods. We find that the proposed framework can successfully mitigate dataset bias, as evinced by extensive evaluations on established diversity metrics, while significantly improving fairness metrics such as equality of opportunity.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Fairness-aware Learning and Face Analysismentioning

confidence: 99%

Section: Fairness-aware Learning and Face Analysismentioning

confidence: 99%

Section: Fairness-aware Learning and Face Analysismentioning

confidence: 99%

See 2 more Smart Citations

Mitigating Demographic Bias in Facial Datasets with Style-Based Multi-attribute Transfer

et al. 2021

View full text Add to dashboard Cite

show abstract

“…There are several ways to enforce fairness in machine learning models: as a pre-processing step (Kamiran and Calders, 2012 ; Zemel et al, 2013 ; Louizos et al, 2016 ; Lum and Johndrow, 2016 ; Chiappa, 2019 ; Quadrianto et al, 2019 ), as a post-processing step (Feldman et al, 2015 ; Hardt et al, 2016 ), or as a constraint during the learning phase (Calders et al, 2009 ; Zafar et al, 2017a , b ; Donini et al, 2018 ; Dimitrakakis et al, 2019 ). Our method enforces fairness during the learning phase (an in-processing approach) but, unlike other approaches, we do not cast fair-learning as a constrained optimization problem.…”

Section: Related Workmentioning

confidence: 99%

Tuning Fairness by Balancing Target Labels

Kehrenberg

Chen

Quadrianto

2020

Front. Artif. Intell.

Self Cite

View full text Add to dashboard Cite

The issue of fairness in machine learning models has recently attracted a lot of attention as ensuring it will ensure continued confidence of the general public in the deployment of machine learning systems. We focus on mitigating the harm incurred by a biased machine learning system that offers better outputs (e.g., loans, job interviews) for certain groups than for others. We show that bias in the output can naturally be controlled in probabilistic models by introducing a latent target output. This formulation has several advantages: first, it is a unified framework for several notions of group fairness such as Demographic Parity and Equality of Opportunity; second, it is expressed as a marginalization instead of a constrained problem; and third, it allows the encoding of our knowledge of what unbiased outputs should be. Practically, the second allows us to avoid unstable constrained optimization procedures and to reuse off-the-shelf toolboxes. The latter translates to the ability to control the level of fairness by directly varying fairness target rates. In contrast, existing approaches rely on intermediate, arguably unintuitive, control parameters such as covariance thresholds.

show abstract