Personality-guided Public-Private Domain Disentangled Hypergraph-Former Network for Multimodal Depression Detection

TL;DR

This paper introduces P$^3$HF, a novel multimodal depression detection model that leverages personality-guided representations, hypergraph reasoning, and domain disentanglement to improve accuracy and robustness across behavioral contexts.

Contribution

The paper presents a new architecture combining personality-guided encoding, hypergraph-based modeling, and contrastive domain disentanglement for enhanced depression detection.

Findings

Achieves 10% accuracy improvement over existing methods.

Validates the importance of personality-guided and hypergraph components.

Demonstrates robustness across diverse behavioral contexts.

Abstract

Depression represents a global mental health challenge requiring efficient and reliable automated detection methods. Current Transformer- or Graph Neural Networks (GNNs)-based multimodal depression detection methods face significant challenges in modeling individual differences and cross-modal temporal dependencies across diverse behavioral contexts. Therefore, we propose P$^3$HF (Personality-guided Public-Private Domain Disentangled Hypergraph-Former Network) with three key innovations: (1) personality-guided representation learning using LLMs to transform discrete individual features into contextual descriptions for personalized encoding; (2) Hypergraph-Former architecture modeling high-order cross-modal temporal relationships; (3) event-level domain disentanglement with contrastive learning for improved generalization across behavioral contexts. Experiments on MPDD-Young dataset show P$^3$HF achieves around 10\% improvement on accuracy and weighted F1 for binary and ternary depression classification task over existing methods. Extensive ablation studies validate the independent contribution of each architectural component, confirming that personality-guided representation learning and high-order hypergraph reasoning are both essential for generating robust, individual-aware depression-related representations. The code is released at https://github.com/hacilab/P3HF.