Multi-task Learning for Brain Network Analysis in the ABCD Study

The Adolescent Brain Cognitive Development study provides a rich data resource for exploring the associations between brain network and cognitive, personality, and mental health measures in adolescents. To leverage this rich dataset, we propose a novel multi-task learning framework that predicts these measures from multi-view brain network data using a graph transformer architecture. Our approach learns shared representations across tasks while allowing for task-specific predictions, improving performance compared to single-task learning. Ablation studies reveal the importance of our proposed techniques of Batch-Wise Loss Balancing and Target Standardization in ensuring successful multi-task learning. Furthermore, we develop innovative visualization techniques based on integrated gradients to interpret the learned task correlations and identify influential brain network edges for each task. Our findings contribute to understanding the complex relationships between brain connectome and behavioral outcomes, highlighting the potential of multi-task learning in this domain. The implementation is available at https://github.com/Wayfear/MTML-ABCD/.