Abstract
Deep learning models have showcased remarkable performances in natural language processing tasks. While much attention has been paid to improvements in utility, privacy leakage and social bias are two major concerns arising in trained models. In this paper, we address both privacy protection and gender bias mitigation in classification models simultaneously. We first introduce a selective privacy-preserving method that obscures individuals’ sensitive information by adding noise to word embeddings. Then, we propose a negative multi-task learning framework to mitigate gender bias, which involves a main task and a gender prediction task. The main task employs a positive loss constraint for utility assurance, while the gender prediction task utilizes a negative loss constraint to remove gender-specific features. We have analyzed four existing word embeddings and evaluated them for sentiment analysis and medical text classification tasks within the proposed negative multi-task learning framework. For instances, RoBERTa achieves the best performance with an average accuracy of 95% for both negative and positive sentiment, with 1.1 disparity score and 1.6 disparity score respectively, and GloVe achieves the best average accuracy of 96.42% with a 0.28 disparity score for the medical task. Our experimental results indicate that our negative multi-task learning framework can effectively mitigate gender bias while maintaining model utility for both sentiment analysis and medical text classification.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Medhat W, Hassan A, Korashy H (2014) Sentiment analysis algorithms and applications: a survey. Ain Shams Eng J 5(4):1093–1113
Lu K, Mardziel P, Wu F, Amancharla P, Datta A (2020) Gender bias in neural natural language processing. Logic, language, and security: essays dedicated to Andre Scedrov on the occasion of his 65th birthday, pp 189–202
Nissim M, van Noord R, van der Goot R (2020) Fair is better than sensational: man is to doctor as woman is to doctor. Comput Linguist 46(2):487–497
Bolukbasi T, Chang K-W, Zou JY, Saligrama V, Kalai AT (2016) Man is to computer programmer as woman is to homemaker? debiasing word embeddings. Adv Neural Inf Process Syst 29
Zhao J, Zhou Y, Li Z, Wang W, Chang K-W (2018) Learning gender-neutral word embeddings. arXiv preprint arXiv:1809.01496
Zhao J, Wang T, Yatskar M, Ordonez V, Chang K-W (2017) Men also like shopping: reducing gender bias amplification using corpus-level constraints. arXiv preprint arXiv:1707.09457
Mo K, Huang T, Xiang X (2020) Querying little is enough: model inversion attack via latent information. In: Chen X, Yan H, Yan Q, Zhang X (eds) Machine learning for cyber security. Springer, Cham, pp 583–591
Sun Y, Liu J, Yu K, Alazab M, Lin K (2021) Pmrss: privacy-preserving medical record searching scheme for intelligent diagnosis in iot healthcare. IEEE Trans Ind Inform 18(3):1981–1990
Hovy D (2015) Demographic factors improve classification performance. In: Proceedings of the 53rd annual meeting of the association for computational linguistics and the 7th international joint conference on natural language processing, vol 1. Long Papers, pp 752–762
Zhao J, Wang T, Yatskar M, Ordonez V, Chang K-W (2018) Gender bias in coreference resolution: evaluation and debiasing methods. arXiv preprint arXiv:1804.06876
Sheng E, Chang K-W, Natarajan P, Peng N (2019) The woman worked as a babysitter: on biases in language generation. arXiv preprint arXiv:1909.01326
Sun T, Gaut A, Tang S, Huang Y, ElSherief M, Zhao J, Mirza D, Belding E, Chang K-W, Wang WY (2019) Mitigating gender bias in natural language processing: literature review. arXiv preprint arXiv:1906.08976
Lalor J, Yang Y, Smith K, Forsgren N, Abbasi A (2022) Benchmarking intersectional biases in NLP. In: Proceedings of the 2022 conference of the North American chapter of the association for computational linguistics: human language technologies. Association for Computational Linguistics, Seattle, United States, pp 3598–3609. https://doi.org/10.18653/v1/2022.naacl-main.263. https://aclanthology.org/2022.naacl-main.263
Savoldi B, Gaido M, Bentivogli L, Negri M, Turchi M (2021) Gender bias in machine translation. Trans Assoc Comput Linguist 9:845–874
Brunet M-E, Alkalay-Houlihan C, Anderson A, Zemel R (2019) Understanding the origins of bias in word embeddings. In: International conference on machine learning. PMLR, pp 803–811
Mikolov T, Sutskever I, Chen K, Corrado GS, Dean J (2013) Distributed representations of words and phrases and their compositionality. Adv Neural Inf Process Syst 26
Pennington J, Socher R, Manning CD (2014) Glove: global vectors for word representation. In: Proceedings of the 2014 conference on empirical methods in natural language processing (EMNLP), pp 1532–1543
Leino K, Fredrikson M (2020) Stolen memories: leveraging model memorization for calibrated \(\{\)White-Box\(\}\) membership inference. In: 29th USENIX security symposium (USENIX Security 20), pp. 1605–1622
Song C, Shmatikov V (2019) Overlearning reveals sensitive attributes. arXiv preprint arXiv:1905.11742
Abadi M, Chu A, Goodfellow I, McMahan HB, Mironov I, Talwar K, Zhang L (2016) Deep learning with differential privacy. In: Proceedings of the 2016 ACM SIGSAC conference on computer and communications security, pp. 308–318
Coavoux M, Narayan S, Cohen SB (2018) Privacy-preserving neural representations of text. arXiv preprint arXiv:1808.09408
Shi W, Cui A, Li E, Jia R, Yu Z (2021) Selective differential privacy for language modeling. arXiv preprint arXiv:2108.12944
Ruder S (2017) An overview of multi-task learning in deep neural networks. arXiv preprint arXiv:1706.05098
Standley T, Zamir A, Chen D, Guibas L, Malik J, Savarese S (2020) Which tasks should be learned together in multi-task learning? In: International conference on machine learning. PMLR, pp 9120–9132
Devlin J, Chang M-W, Lee K, Toutanova K (2018) Bert: pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805
Liu Y, Ott M, Goyal N, Du J, Joshi M, Chen D, Levy O, Lewis M, Zettlemoyer L, Stoyanov V (2019) Roberta: a robustly optimized bert pretraining approach. arXiv preprint arXiv:1907.11692
Hardt M, Price E, Srebro N (2016) Equality of opportunity in supervised learning. Adv neural inf process syst 29
Author information
Authors and Affiliations
Contributions
All authors contributed to the study conception and design. The first draft of the manuscript was written by LG and all authors commented on previous versions of the manuscript. All authors read and approved the final manuscript.
Corresponding author
Ethics declarations
Conflict of interest
The authors declare no competing interests.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Gao, L., Zhan, H. & Sheng, V.S. Mitigate Gender Bias Using Negative Multi-task Learning. Neural Process Lett 55, 11131–11146 (2023). https://doi.org/10.1007/s11063-023-11368-0
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11063-023-11368-0