Data-Efficient Model for Psychological Resilience Prediction based on Neurological Data

2025-02-03

AI Summary

To address key bottlenecks in psychological resilience assessment—including subjectivity inherent in self-report scales, underutilization of neurobiological markers, and scarcity of high-quality neural data—this study proposes a highly robust predictive model tailored for small-sample neuroimaging data. Methodologically, we introduce the first neural Kolmogorov–Arnold network architecture, integrating trait-guided multimodal representation learning with noise-aware inference and an intelligent patch-wise learning strategy to enable effective modeling under low signal-to-noise ratios. Extensive experiments on both public and newly curated neural datasets demonstrate statistically significant improvements over state-of-the-art baselines. Our approach not only enhances the accuracy and interpretability of individual-level resilience prediction but also generates multiple empirically testable hypotheses in psychology. By bridging neuroscientific measurement with psychological theory, this work establishes a novel paradigm for biopsychosocial interdisciplinary research.

Technology Category

• Cognitive Modeling & Cognitive Systems: (Computational) Cognitive Architectures
• Machine Learning: Neuro-Symbolic Learning
• Natural Language Processing: Safety and Robustness

Application Category

• User Modeling, Personalization and Recommendation: Psychology-informed user models and recommender systems
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Web Mining and Content Analysis: Large pretrained models with web data

Abstract

Psychological resilience, defined as the ability to rebound from adversity, is crucial for mental health. Compared with traditional resilience assessments through self-reported questionnaires, resilience assessments based on neurological data offer more objective results with biological markers, hence significantly enhancing credibility. This paper proposes a novel data-efficient model to address the scarcity of neurological data. We employ Neuro Kolmogorov-Arnold Networks as the structure of the prediction model. In the training stage, a new trait-informed multimodal representation algorithm with a smart chunk technique is proposed to learn the shared latent space with limited data. In the test stage, a new noise-informed inference algorithm is proposed to address the low signal-to-noise ratio of the neurological data. The proposed model not only shows impressive performance on both public datasets and self-constructed datasets but also provides some valuable psychological hypotheses for future research.

Problem

• Brain-based Model
• Psychological Resilience
• Prediction Accuracy

Innovation

• Neuropsychological Resilience Prediction
• Kolmogorov-Arnold Neural Networks
• Noise Resilient Modeling