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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Sneh, Aditya, Sahu, Nilesh Kumar, Shelke, Anushka Sanjay, Adyasha, Arya, Lone, Haroon R.
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918193646272512
author Sneh, Aditya
Sahu, Nilesh Kumar
Shelke, Anushka Sanjay
Adyasha, Arya
Lone, Haroon R.
author_facet Sneh, Aditya
Sahu, Nilesh Kumar
Shelke, Anushka Sanjay
Adyasha, Arya
Lone, Haroon R.
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2511_06988
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle HCFSLN: Adaptive Hyperbolic Few-Shot Learning for Multimodal Anxiety Detection
Sneh, Aditya
Sahu, Nilesh Kumar
Shelke, Anushka Sanjay
Adyasha, Arya
Lone, Haroon R.
Machine Learning
Human-Computer Interaction
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.
title HCFSLN: Adaptive Hyperbolic Few-Shot Learning for Multimodal Anxiety Detection
topic Machine Learning
Human-Computer Interaction
url https://arxiv.org/abs/2511.06988