Abstract
Machine learning (ML) bias in mental health detection and analysis is becoming an increasingly pertinent challenge. Despite promising efforts indicating that multimodal methods work better than unimodal methods, there is minimal work on multimodal fairness for depression detection. We propose a causal multimodal framework which consists of two modules. Module 1 performs causal interventional debiasing via backdoor adjustment for each modality to achieve group fairness. Module 2 adaptively fuses the different modalities using a referee-based individual fairness guided fusion mechanism to address individual fairness. We conduct experiments and ablation studies on three depression datasets, D-Vlog, DAIC-WOZ and E-DAIC, and show that our framework improves classification performance as well as group and individual fairness compared to existing approaches.
Keywords
- AI Ethics, Trust, Fairness: General
- Machine Learning: General
- Multidisciplinary Topics and Applications: General
