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

2025-11-16

AI Summary

To address insufficient individualized modeling and challenges in capturing cross-modal temporal dependencies in multimodal depression detection, this paper proposes a persona-guided high-order hypergraph temporal modeling framework. Methodologically: (1) personalized behavioral descriptions are generated via large language models to enable fine-grained individual representation encoding; (2) a Hypergraph-Former architecture is designed to model dynamic, high-order temporal associations among multimodal signals; (3) an event-level public-private domain contrastive disentanglement mechanism is introduced to enhance generalization across heterogeneous behavioral contexts. Evaluated on the MPDD-Young dataset, the framework achieves approximately 10% improvements in both accuracy and weighted F1-score for binary and ternary classification tasks. Ablation studies confirm the critical contributions of each component to individual-aware modeling.

Technology Category

Machine Learning: Multimodal LearningComputer Vision: Multi-modal VisionNatural Language Processing: Language Grounding & Multi-modal NLP

Application Category

User Modeling, Personalization and Recommendation: Studies of user behavior, including longitudinal effects of personalized systemsWeb Mining and Content Analysis: Mining multimedia, multimodal, multilingual, cross-lingual Web dataGraph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

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.

Problem

• Modeling individual differences in multimodal depression detection methods
• Capturing cross-modal temporal dependencies across behavioral contexts
• Improving generalization across diverse depression detection scenarios

Innovation

• Personality-guided representation learning using LLMs
• Hypergraph-Former modeling high-order cross-modal relationships
• Event-level domain disentanglement with contrastive learning