paper-with-me

홈 › Papers

Towards Reducing Bias in Gender Classification

2019-11-16 · Komal K. Teru, Aishik Chakraborty

Societal bias towards certain communities is a big problem that affects a lot of machine learning systems. This work aims at addressing the racial bias present in many modern gender recognition systems. We learn race invariant representations of human faces with an adversarially trained autoencoder model. We show that such representations help us achieve less biased performance in gender classification. We use variance in classification accuracy across different races as a surrogate for the racial bias of the model and achieve a drop of over 40% in variance with race invariant representations.

📄 PDF Abstract BibTeX arXiv:1911.08556

Code (0)

등록된 구현이 없습니다.

Tasks

BIG-bench Machine LearningClassificationGender ClassificationGeneral Classification

Methods 이 논문이 사용한 방법론

Solana Customer Service Number +1-833-534-1729 설명 없음

Similar Papers 제목 키워드 기반

Deep Generative Views to Mitigate Gender Classification Bias Across Gender-Race Groups

2022-08-17 · Sreeraj Ramachandran, Ajita Rattani

Published studies have suggested the bias of automated face-based gender classification algorithms across gender-race groups. Specifically, unequal accuracy rates were obtained for women and dark-skinned people. To mitig…

ClassificationFacial Attribute ClassificationFairnessGender Classification

A Causal Inference Method for Reducing Gender Bias in Word Embedding Relations

2019-11-25 · Zekun Yang, Juan Feng

Word embedding has become essential for natural language processing as it boosts empirical performances of various tasks. However, recent research discovers that gender bias is incorporated in neural word embeddings, and…

Causal Inferencecoreference-resolutionCoreference ResolutionSentence+1

Interpretable bias mitigation for textual data: Reducing gender bias in patient notes while maintaining classification performance

2021-03-10 · Joshua R. Minot, Nicholas Cheney, Marc Maier, Danne C. Elbers 외

Medical systems in general, and patient treatment decisions and outcomes in particular, are affected by bias based on gender and other demographic elements. As language models are increasingly applied to medicine, there …

Data AugmentationFairness

Identifying and Reducing Gender Bias in Word-Level Language Models

2019-04-05 · NAACL 2019 6 · Shikha Bordia, Samuel R. Bowman

Many text corpora exhibit socially problematic biases, which can be propagated or amplified in the models trained on such data. For example, doctor cooccurs more frequently with male pronouns than female pronouns. In thi…

Language ModelingLanguage Modelling

Reducing Gender Bias in Word-Level Language Models with a Gender-Equalizing Loss Function

2019-05-30 · ACL 2019 7 · Yusu Qian, Urwa Muaz, Ben Zhang, Jae Won Hyun

Gender bias exists in natural language datasets which neural language models tend to learn, resulting in biased text generation. In this research, we propose a debiasing approach based on the loss function modification. …

Data AugmentationText Generation