Repository logo
 

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

Accepted version
Peer-reviewed

Type

Conference Object

Change log

Authors

Cheong, Jiaee 
Kalkan, Sinan 

Abstract

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.

Description

Keywords

Journal Title

Conference Name

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

Journal ISSN

Volume Title

Publisher

Publisher DOI

Publisher URL

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