{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,20]],"date-time":"2026-07-20T17:52:48Z","timestamp":1784569968848,"version":"3.55.0"},"reference-count":36,"publisher":"MDPI AG","issue":"4","license":[{"start":{"date-parts":[[2022,3,29]],"date-time":"2022-03-29T00:00:00Z","timestamp":1648512000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Future Internet"],"abstract":"<jats:p>Although deep learning has proven to be tremendously successful, the main issue is the dependency of its performance on the quality and quantity of training datasets. Since the quality of data can be affected by biases, a novel deep learning method based on decorrelation is presented in this study. The decorrelation specifically learns bias invariant features by reducing the non-linear statistical dependency between features and bias itself. This makes the deep learning models less prone to biased decisions by addressing data bias issues. We introduce Decorrelated Deep Neural Networks (DcDNN) or Decorrelated Convolutional Neural Networks (DcCNN) and Decorrelated Artificial Neural Networks (DcANN) by applying decorrelation-based optimization to Deep Neural Networks (DNN) and Artificial Neural Networks (ANN), respectively. Previous bias mitigation methods result in a drastic loss in accuracy at the cost of bias reduction. Our study aims to resolve this by controlling how strongly the decorrelation function for bias reduction and loss function for accuracy affect the network objective function. The detailed analysis of the hyperparameter shows that for the optimal value of hyperparameter, our model is capable of maintaining accuracy while being bias invariant. The proposed method is evaluated on several benchmark datasets with different types of biases such as age, gender, and color. Additionally, we test our approach along with traditional approaches to analyze the bias mitigation in deep learning. Using simulated datasets, the results of t-distributed stochastic neighbor embedding (t-SNE) of the proposed model validated the effective removal of bias. An analysis of fairness metrics and accuracy comparisons shows that using our proposed models reduces the biases without compromising accuracy significantly. Furthermore, the comparison of our method with existing methods shows the superior performance of our model in terms of bias mitigation, as well as simplicity of training.<\/jats:p>","DOI":"10.3390\/fi14040110","type":"journal-article","created":{"date-parts":[[2022,3,29]],"date-time":"2022-03-29T21:44:52Z","timestamp":1648590292000},"page":"110","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["Decorrelation-Based Deep Learning for Bias Mitigation"],"prefix":"10.3390","volume":"14","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3679-3685","authenticated-orcid":false,"given":"Pranita","family":"Patil","sequence":"first","affiliation":[{"name":"Department of Analytics, Harrisburg University of Science and Technology, Harrisburg, PA 17101, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6046-2774","authenticated-orcid":false,"given":"Kevin","family":"Purcell","sequence":"additional","affiliation":[{"name":"Department of Analytics, Harrisburg University of Science and Technology, Harrisburg, PA 17101, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2022,3,29]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3457607","article-title":"A survey on bias and fairness in machine learning","volume":"54","author":"Mehrabi","year":"2021","journal-title":"ACM Comput. Surv. (CSUR)"},{"key":"ref_2","unstructured":"K\u00e4rkk\u00e4inen, K., and Joo, J. (2019). Fairface: Face attribute dataset for balanced race, gender, and age. arXiv."},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Tommasi, T., Patricia, N., Caputo, B., and Tuytelaars, T. (2017). A deeper look at dataset bias. Domain Adaptation in Computer Vision Applications, Springer.","DOI":"10.1007\/978-3-319-58347-1_2"},{"key":"ref_4","unstructured":"LeCun, Y., Boser, B., Denker, J., Henderson, D., Howard, R., Hubbard, W., and Jackel, L. (1989, January 27\u201330). Handwritten digit recognition with a back-propagation network. Proceedings of the Advances in Neural Information Processing Systems, Denver, CO, USA."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1007\/s10115-011-0463-8","article-title":"Data preprocessing techniques for classification without discrimination","volume":"33","author":"Kamiran","year":"2012","journal-title":"Knowl. Inf. Syst."},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Kim, B., Kim, H., Kim, K., Kim, S., and Kim, J. (2019, January 15\u201320). Learning not to learn: Training deep neural networks with biased data. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Long Beach, CA, USA.","DOI":"10.1109\/CVPR.2019.00922"},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Adeli, E., Zhao, Q., Pfefferbaum, A., Sullivan, E.V., Fei-Fei, L., Niebles, J.C., and Pohl, K.M. (2021, January 3\u20138). Representation learning with statistical independence to mitigate bias. Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, Waikoloa, HI, USA.","DOI":"10.1109\/WACV48630.2021.00256"},{"key":"ref_8","unstructured":"Hagan, M.T., Demuth, H.B., and Beale, M. (1997). Neural Network Design, PWS Publishing Co."},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Kasieczka, G., and Shih, D. (2020). DisCo Fever: Robust Networks through Distance Correlation. arXiv.","DOI":"10.1103\/PhysRevLett.125.122001"},{"key":"ref_10","unstructured":"Calmon, F., Wei, D., Vinzamuri, B., Natesan Ramamurthy, K., and Varshney, K.R. (2017, January 4\u20139). Optimized pre-processing for discrimination prevention. Proceedings of the Advances in Neural Information Processing Systems, Long Beach, CA, USA."},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Li, Y., and Vasconcelos, N. (2019, January 15\u201320). Repair: Removing representation bias by dataset resampling. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Long Beach, CA, USA.","DOI":"10.1109\/CVPR.2019.00980"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"117689","DOI":"10.1016\/j.neuroimage.2020.117689","article-title":"Deep learning-based unlearning of dataset bias for MRI harmonisation and confound removal","volume":"228","author":"Dinsdale","year":"2021","journal-title":"NeuroImage"},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Zhang, B.H., Lemoine, B., and Mitchell, M. (2018, January 2\u20133). Mitigating unwanted biases with adversarial learning. Proceedings of the 2018 AAAI\/ACM Conference on AI, Ethics, and Society, New Orleans, LA, USA.","DOI":"10.1145\/3278721.3278779"},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Mandis, I.S. (2021, November 15). Reducing Racial and Gender Bias in Machine Learning and Natural Language Processing Tasks Using a GAN Approach. Available online: https:\/\/terra-docs.s3.us-east-2.amazonaws.com\/IJHSR\/Articles\/volume3-issue6\/2021_36_p17_Mandis.pdf.","DOI":"10.36838\/v3i6.5"},{"key":"ref_15","unstructured":"Goodfellow, I., Pouget-Abadie, J., Mirza, M., Xu, B., Warde-Farley, D., Ozair, S., Courville, A., and Bengio, Y. (2014, January 8\u201313). Generative adversarial nets. Proceedings of the Advances in Neural Information Processing Systems, Montreal, QC, Canada."},{"key":"ref_16","unstructured":"Sadeghi, B., Yu, R., and Boddeti, V. (November, January 27). On the global optima of kernelized adversarial representation learning. Proceedings of the IEEE\/CVF International Conference on Computer Vision, Seoul, Korea."},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Zhao, T., Dai, E., Shu, K., and Wang, S. (2022, January 20). Towards Fair Classifiers without Sensitive Attributes: Exploring Biases in Related Features. Available online: http:\/\/www.cs.iit.edu\/~kshu\/files\/fair-wsdm22.pdf.","DOI":"10.1145\/3488560.3498493"},{"key":"ref_18","unstructured":"Wang, T., Zhao, J., Yatskar, M., Chang, K.W., and Ordonez, V. (November, January 27). Balanced datasets are not enough: Estimating and mitigating gender bias in deep image representations. Proceedings of the IEEE\/CVF International Conference on Computer Vision, Seoul, Korea."},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Alvi, M., Zisserman, A., and Nell\u00e5ker, C. (2018, January 8\u201314). Turning a blind eye: Explicit removal of biases and variation from deep neural network embeddings. Proceedings of the European Conference on Computer Vision (ECCV) Workshops, Munich, Germany.","DOI":"10.1007\/978-3-030-11009-3_34"},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Wang, R., Karimi, A.H., and Ghodsi, A. (2018, January 8\u201313). Distance correlation autoencoder. Proceedings of the IEEE 2018 International Joint Conference on Neural Networks (IJCNN), Rio de Janeiro, Brazil.","DOI":"10.1109\/IJCNN.2018.8489291"},{"key":"ref_21","first-page":"59","article-title":"Thirteen ways to look at the correlation coefficient","volume":"42","author":"Nicewander","year":"1988","journal-title":"Am. Stat."},{"key":"ref_22","first-page":"2769","article-title":"Measuring and testing dependence by correlation of distances","volume":"35","author":"Rizzo","year":"2007","journal-title":"Ann. Stat."},{"key":"ref_23","unstructured":"Patil, P. (2013). Flexible Image Recognition Software Toolbox (First), Oklahoma State University."},{"key":"ref_24","unstructured":"Dua, D., and Graff, C. (2020, August 01). UCI Machine Learning Repository. (University of California, Irvine, School of Information, 2017). Available online: http:\/\/archive.ics.uci.edu\/ml."},{"key":"ref_25","unstructured":"LeCun, Y., and Cortes, C. (2020, July 25). MNIST Handwritten Digit Database. Available online: http:\/\/yann.lecun.com\/exdb\/mnist\/."},{"key":"ref_26","unstructured":"Arjovsky, M., Bottou, L., Gulrajani, I., and Lopez-Paz, D. (2019). Invariant risk minimization. arXiv."},{"key":"ref_27","unstructured":"(2019, February 12). Deep Learning Ami\u2014Developer Guide. AWS Deep Learning AMIs Documentation. Available online: https:\/\/docs.aws.amazon.com\/dlami\/latest\/devguide\/dlami-dg.pdf."},{"key":"ref_28","unstructured":"Abadi, M., Agarwal, A., Barham, P., Brevdo, E., Chen, Z., Citro, C., Corrado, G., Davis, A., Dean, J., and Devin, M. (2019, January 06). TensorFlow: Large-Scale Machine Learning on Heterogeneous Systems. Available online: https:\/\/www.tensorflow.org\/."},{"key":"ref_29","unstructured":"Chetlur, S., Woolley, C., Vandermersch, P., Cohen, J., Tran, J., Catanzaro, B., and Shelhamer, E. (2014). Cudnn: Efficient primitives for deep learning. arXiv."},{"key":"ref_30","unstructured":"Kusner, M.J., Loftus, J., Russell, C., and Silva, R. (2017, January 4\u20139). Counterfactual fairness. Proceedings of the Advances in Neural Information Processing Systems, Long Beach, CA, USA."},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Feldman, M., Friedler, S.A., Moeller, J., Scheidegger, C., and Venkatasubramanian, S. (2015, January 10\u201313). Certifying and removing disparate impact. Proceedings of the 21th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, Sydney, Australia.","DOI":"10.1145\/2783258.2783311"},{"key":"ref_32","unstructured":"Li, X., Cui, Z., Wu, Y., Gu, L., and Harada, T. (2021). Estimating and improving fairness with adversarial learning. arXiv."},{"key":"ref_33","unstructured":"Bellamy, R.K., Dey, K., Hind, M., Hoffman, S.C., Houde, S., Kannan, K., Lohia, P., Martino, J., Mehta, S., and Mojsilovic, A. (2018). AI Fairness 360: An extensible toolkit for detecting, understanding, and mitigating unwanted algorithmic bias. arXiv."},{"key":"ref_34","unstructured":"Feldman, T., and Peake, A. (2021). End-To-End Bias Mitigation: Removing Gender Bias in Deep Learning. arXiv."},{"key":"ref_35","unstructured":"Pleiss, G., Raghavan, M., Wu, F., Kleinberg, J., and Weinberger, K.Q. (2017, January 4\u20139). On fairness and calibration. Proceedings of the Advances in Neural Information Processing Systems, Long Beach, CA, USA."},{"key":"ref_36","first-page":"2096","article-title":"Domain-adversarial training of neural networks","volume":"17","author":"Ganin","year":"2016","journal-title":"J. Mach. Learn. Res."}],"container-title":["Future Internet"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1999-5903\/14\/4\/110\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T22:45:40Z","timestamp":1760136340000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1999-5903\/14\/4\/110"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,3,29]]},"references-count":36,"journal-issue":{"issue":"4","published-online":{"date-parts":[[2022,4]]}},"alternative-id":["fi14040110"],"URL":"https:\/\/doi.org\/10.3390\/fi14040110","relation":{},"ISSN":["1999-5903"],"issn-type":[{"value":"1999-5903","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,3,29]]}}}