Multi-Task Learning with Feature-Similarity Laplacian Graphs for Predicting Alzheimer's Disease Progression

2025-10-11

AI Summary

Existing multi-task learning approaches for Alzheimer’s disease (AD) progression prediction neglect the time-varying nature of feature correlations, leading to inaccurate modeling and limited biological interpretability. To address this, we propose a Dynamic Feature Similarity Laplacian Regularization framework: (1) we construct a time-evolving feature similarity graph to explicitly capture dynamically changing feature associations in longitudinal neuroimaging data; (2) we design a Laplacian penalty term that jointly enforces temporal smoothness across tasks, enabling unified multi-task optimization; and (3) we employ the Alternating Direction Method of Multipliers (ADMM) to efficiently solve the resulting objective with non-smooth regularization. Evaluated on the ADNI dataset, our method significantly outperforms state-of-the-art baselines in both prediction accuracy (e.g., lower RMSE for hippocampal atrophy and cognitive scores) and biological plausibility—revealing temporally consistent, neuroanatomically meaningful feature relationships. The implementation is publicly available.

Technology Category

• Machine Learning: Transfer, Domain Adaptation, Multi-Task Learning
• Natural Language Processing: Learning & Optimization for NLP
• Computer Vision: Learning & Optimization for CV

Application Category

• Graph Algorithms and Modeling for the Web: Algorithms and analysis for heterogeneous, signed, attributed, multi-relational, temporal, higher-order, and annotated Web-related graphs
• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Alzheimer's Disease (AD) is the most prevalent neurodegenerative disorder in aging populations, posing a significant and escalating burden on global healthcare systems. While Multi-Tusk Learning (MTL) has emerged as a powerful computational paradigm for modeling longitudinal AD data, existing frameworks do not account for the time-varying nature of feature correlations. To address this limitation, we propose a novel MTL framework, named Feature Similarity Laplacian graph Multi-Task Learning (MTL-FSL). Our framework introduces a novel Feature Similarity Laplacian (FSL) penalty that explicitly models the time-varying relationships between features. By simultaneously considering temporal smoothness among tasks and the dynamic correlations among features, our model enhances both predictive accuracy and biological interpretability. To solve the non-smooth optimization problem arising from our proposed penalty terms, we adopt the Alternating Direction Method of Multipliers (ADMM) algorithm. Experiments conducted on the Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset demonstrate that our proposed MTL-FSL framework achieves state-of-the-art performance, outperforming various baseline methods. The implementation source can be found at https://github.com/huatxxx/MTL-FSL.

Problem

• Modeling time-varying feature correlations in Alzheimer's progression
• Enhancing predictive accuracy and biological interpretability simultaneously
• Addressing non-smooth optimization in multi-task learning frameworks

Innovation

• Uses Feature Similarity Laplacian graphs for time-varying feature relationships
• Incorporates temporal smoothness and dynamic feature correlations simultaneously
• Solves optimization with Alternating Direction Method of Multipliers algorithm