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

We propose accounting for this gender difference in PHQ-8 distributions via U-Fair. Moreover, each gender may display different PHQ-approach towards building relevant ML for healthcare 8 task distribution which may results in different solutions, we propose a novel method, U-Fair, which PHQ-8 distribution and variance. Although investigation accounts for the gender difference in PHQ-8 distribution on the relationship between the PHQ-8 and and leverages on uncertainty as a MTL task gender has been explored in other fields such as psychiatry reweighing mechanism to achieve better gender fairness (Thibodeau and Asmundson, 2014; Vetter for depression detection. Our key contributions et al., 2013; Leung et al., 2020), this has not been investigated are as follow: nor accounted for in any of the existing ML We conduct the first analysis to investigate how for depression detection methods. Moreover, existing MTL impacts fairness in depression detection by work has demonstrated the risk of a fairness-accuracy using each PHQ-8 subcriterion as a task. We trade-off (Pleiss et al., 2017) and how mainstream show that a simplistic baseline MTL approach MTL objectives might not correlate well with fairness runs the risk of incurring negative transfer and goals (Wang et al., 2021b). No work has investigated may not improve on the Pareto frontier. A how a MTL approach impacts performance Pareto frontier can be understood as the set of across fairness for the task of depression detection.