FedKD4DD: Federated Knowledge Distillation for Depression Detection

Aslam Jlassi, Afef Mdhaffar, Afef Mdhaffar, Mohamed Jmaiel, Mohamed Jmaiel, Bernd Freisleben

2025

Abstract

Depression affects over 280 million people globally and requires timely, accurate intervention to mitigate its effects. Traditional diagnostic methods often introduce delays and privacy concerns due to centralized data processing and subjective evaluations. To address these challenges, we propose a smartphone-based approach that uses federated learning to detect depressive episodes through the analysis of spontaneous phone calls. Our proposal protects user privacy by retaining data locally on user devices (i.e., smartphones). Our approach addresses catastrophic forgetting through the use of knowledge distillation, enabling efficient storage and robust learning. The experimental results demonstrate reasonable accuracy with minimal resource consumption, highlighting the potential of privacy-preserving AI solutions for mental health monitoring.

Paper Citation

in Harvard Style

Jlassi A., Mdhaffar A., Jmaiel M. and Freisleben B. (2025). FedKD4DD: Federated Knowledge Distillation for Depression Detection. In Proceedings of the 17th International Conference on Agents and Artificial Intelligence - Volume 3: ICAART; ISBN 978-989-758-737-5, SciTePress, pages 1473-1480. DOI: 10.5220/0013388200003890

in Bibtex Style

@conference{icaart25,
author={Aslam Jlassi and Afef Mdhaffar and Mohamed Jmaiel and Bernd Freisleben},
title={FedKD4DD: Federated Knowledge Distillation for Depression Detection},
booktitle={Proceedings of the 17th International Conference on Agents and Artificial Intelligence - Volume 3: ICAART},
year={2025},
pages={1473-1480},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0013388200003890},
isbn={978-989-758-737-5},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 17th International Conference on Agents and Artificial Intelligence - Volume 3: ICAART
TI - FedKD4DD: Federated Knowledge Distillation for Depression Detection
SN - 978-989-758-737-5
AU - Jlassi A.
AU - Mdhaffar A.
AU - Jmaiel M.
AU - Freisleben B.
PY - 2025
SP - 1473
EP - 1480
DO - 10.5220/0013388200003890
PB - SciTePress