HCFSLN: Adaptive Hyperbolic Few-Shot Learning for Multimodal Anxiety Detection

TL;DR

This paper introduces HCFSLN, a hyperbolic few-shot learning framework that effectively detects anxiety using multimodal data with minimal samples, outperforming existing methods significantly.

Contribution

The paper presents a novel hyperbolic embedding-based FSL model for multimodal anxiety detection, addressing data scarcity and improving classification accuracy.

Findings

Achieved 88% accuracy in anxiety detection

Outperformed six baseline models by 14%

Demonstrated effectiveness of hyperbolic space for anxiety modeling

Abstract

Anxiety disorders impact millions globally, yet traditional diagnosis relies on clinical interviews, while machine learning models struggle with overfitting due to limited data. Large-scale data collection remains costly and time-consuming, restricting accessibility. To address this, we introduce the Hyperbolic Curvature Few-Shot Learning Network (HCFSLN), a novel Few-Shot Learning (FSL) framework for multimodal anxiety detection, integrating speech, physiological signals, and video data. HCFSLN enhances feature separability through hyperbolic embeddings, cross-modal attention, and an adaptive gating network, enabling robust classification with minimal data. We collected a multimodal anxiety dataset from 108 participants and benchmarked HCFSLN against six FSL baselines, achieving 88% accuracy, outperforming the best baseline by 14%. These results highlight the effectiveness of hyperbolic space for modeling anxiety-related speech patterns and demonstrate FSL's potential for anxiety classification.