Repository logo

FairReFuse: Referee-Guided Fusion for Multi-Modal Causal Fairness in Depression Detection

Accepted version


Conference Object

Change log


Cheong, Jiaee 
Kalkan, Sinan 


Machine learning (ML) bias in mental health detection and analysis is becoming an increasingly pertinent challenge. Despite promising efforts indicating that multimodal methods often work better than unimodal methods, there has been minimal work on multimodal fairness for depression detection. We propose a causal multimodal framework which consists of two separate 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.



Journal Title

Conference Name

The 33rd International Joint Conference on Artificial Intelligence (IJCAI 2024)

Journal ISSN

Volume Title


Publisher DOI

Publisher URL

Engineering and Physical Sciences Research Council (EP/R030782/1)
Alan Turing Institute (ATIPO000004438)
The Alan Turing PhD Studentship The Leverhulme Trust Study Abroad Studentship