Learning to Route: Per-Sample Adaptive Routing for Multimodal Multitask Prediction.

Publication Type	Academic Article
Authors	Ajirak M, Bein O, Bowen E, Kanellopoulos D, Falk A, Gunning F, Solomonov N, Grosenick L
Journal	Adv Neural Inf Process Syst
Volume	38
Pagination	68521-68549
Date Published	12/01/2025
ISSN	1049-5258
Abstract	We propose a unified framework for adaptive routing in multitask, multimodal prediction settings where data heterogeneity and task interactions vary across samples. We introduce a routing-based architecture that dynamically selects modality processing pathways and task-sharing strategies on a per-sample basis. Our model defines multiple modality paths, including raw and fused representations of text and numeric features, and learns to route each input through the most informative modality-task expert combination. Task-specific predictions are produced by shared or independent heads depending on the routing decision, and the entire system is trained end-to-end. We evaluate the model on both synthetic data and real-world psychotherapy notes, predicting depression and anxiety outcomes. Our experiments show that our method consistently outperforms fixed multitask or single-task baselines, and that the learned routing policy provides interpretable insights into modality relevance and task structure. This addresses critical challenges in personalized healthcare by providing per-subject adaptive information processing that accounts for data and task correlation heterogeneity.
PubMed ID	42253361
PubMed Central ID	PMC13241019