U-Fair: Uncertainty-based Multimodal Multitask Learning for Fairer Depression Detection

Jiaee Cheong, Aditya Bangar, Sinan Kalkan, Hatice Gunes
Proceedings of the 4th Machine Learning for Health Symposium, PMLR 259:203-218, 2025.

Abstract

Machine learning bias in mental health is becoming an increasingly pertinent challenge. Despite promising efforts indicating that multitask approaches often work better than unitask approaches, there is minimal work investigating the impact of multitask learning on performance and fairness in depression detection nor leveraged it to achieve fairer prediction outcomes. In this work, we undertake a systematic investigation of using a multitask approach to improve performance and fairness for depression detection. We propose a novel gender-based task-reweighting method using uncertainty grounded in how the PHQ-8 questionnaire is structured. Our results indicate that, although a multitask approach improves performance and fairness compared to a unitask approach, the results are not always consistent and we see evidence of negative transfer and a reduction in the Pareto frontier, which is concerning given the high-stake healthcare setting. Our proposed approach of gender-based reweighting with uncertainty improves performance and fairness and alleviates both challenges to a certain extent. Our findings on each PHQ-8 subitem task difficulty are also in agreement with the largest study conducted on the PHQ-8 subitem discrimination capacity, thus providing the very first tangible evidence linking ML findings with large-scale empirical population studies conducted on the PHQ-8.

Cite this Paper


BibTeX
@InProceedings{pmlr-v259-cheong25a, title = {U-Fair: Uncertainty-based Multimodal Multitask Learning for Fairer Depression Detection}, author = {Cheong, Jiaee and Bangar, Aditya and Kalkan, Sinan and Gunes, Hatice}, booktitle = {Proceedings of the 4th Machine Learning for Health Symposium}, pages = {203--218}, year = {2025}, editor = {Hegselmann, Stefan and Zhou, Helen and Healey, Elizabeth and Chang, Trenton and Ellington, Caleb and Mhasawade, Vishwali and Tonekaboni, Sana and Argaw, Peniel and Zhang, Haoran}, volume = {259}, series = {Proceedings of Machine Learning Research}, month = {15--16 Dec}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v259/main/assets/cheong25a/cheong25a.pdf}, url = {https://proceedings.mlr.press/v259/cheong25a.html}, abstract = {Machine learning bias in mental health is becoming an increasingly pertinent challenge. Despite promising efforts indicating that multitask approaches often work better than unitask approaches, there is minimal work investigating the impact of multitask learning on performance and fairness in depression detection nor leveraged it to achieve fairer prediction outcomes. In this work, we undertake a systematic investigation of using a multitask approach to improve performance and fairness for depression detection. We propose a novel gender-based task-reweighting method using uncertainty grounded in how the PHQ-8 questionnaire is structured. Our results indicate that, although a multitask approach improves performance and fairness compared to a unitask approach, the results are not always consistent and we see evidence of negative transfer and a reduction in the Pareto frontier, which is concerning given the high-stake healthcare setting. Our proposed approach of gender-based reweighting with uncertainty improves performance and fairness and alleviates both challenges to a certain extent. Our findings on each PHQ-8 subitem task difficulty are also in agreement with the largest study conducted on the PHQ-8 subitem discrimination capacity, thus providing the very first tangible evidence linking ML findings with large-scale empirical population studies conducted on the PHQ-8.} }
Endnote
%0 Conference Paper %T U-Fair: Uncertainty-based Multimodal Multitask Learning for Fairer Depression Detection %A Jiaee Cheong %A Aditya Bangar %A Sinan Kalkan %A Hatice Gunes %B Proceedings of the 4th Machine Learning for Health Symposium %C Proceedings of Machine Learning Research %D 2025 %E Stefan Hegselmann %E Helen Zhou %E Elizabeth Healey %E Trenton Chang %E Caleb Ellington %E Vishwali Mhasawade %E Sana Tonekaboni %E Peniel Argaw %E Haoran Zhang %F pmlr-v259-cheong25a %I PMLR %P 203--218 %U https://proceedings.mlr.press/v259/cheong25a.html %V 259 %X Machine learning bias in mental health is becoming an increasingly pertinent challenge. Despite promising efforts indicating that multitask approaches often work better than unitask approaches, there is minimal work investigating the impact of multitask learning on performance and fairness in depression detection nor leveraged it to achieve fairer prediction outcomes. In this work, we undertake a systematic investigation of using a multitask approach to improve performance and fairness for depression detection. We propose a novel gender-based task-reweighting method using uncertainty grounded in how the PHQ-8 questionnaire is structured. Our results indicate that, although a multitask approach improves performance and fairness compared to a unitask approach, the results are not always consistent and we see evidence of negative transfer and a reduction in the Pareto frontier, which is concerning given the high-stake healthcare setting. Our proposed approach of gender-based reweighting with uncertainty improves performance and fairness and alleviates both challenges to a certain extent. Our findings on each PHQ-8 subitem task difficulty are also in agreement with the largest study conducted on the PHQ-8 subitem discrimination capacity, thus providing the very first tangible evidence linking ML findings with large-scale empirical population studies conducted on the PHQ-8.
APA
Cheong, J., Bangar, A., Kalkan, S. & Gunes, H.. (2025). U-Fair: Uncertainty-based Multimodal Multitask Learning for Fairer Depression Detection. Proceedings of the 4th Machine Learning for Health Symposium, in Proceedings of Machine Learning Research 259:203-218 Available from https://proceedings.mlr.press/v259/cheong25a.html.

Related Material