Tensorized Multi-Task Learning for Personalized Modeling of Heterogeneous Individuals with High-Dimensional Data

TL;DR

This paper introduces a tensorized multi-task learning framework that effectively models heterogeneous subpopulations with high-dimensional data, improving personalization, accuracy, and interpretability by capturing shared and unique task structures.

Contribution

It presents a novel low-rank tensor decomposition approach within multi-task learning for personalized modeling of diverse subpopulations, outperforming existing benchmarks.

Findings

Superior prediction accuracy in simulations and case studies

Effective capturing of shared and individual subpopulation patterns

Enhanced interpretability of personalized models

Abstract

Effective modeling of heterogeneous subpopulations presents a significant challenge due to variations in individual characteristics and behaviors. This paper proposes a novel approach to address this issue through multi-task learning (MTL) and low-rank tensor decomposition techniques. Our MTL approach aims to enhance personalized modeling by leveraging shared structures among similar tasks while accounting for distinct subpopulation-specific variations. We introduce a framework where low-rank decomposition decomposes the collection of task model parameters into a low-rank structure that captures commonalities and variations across tasks and subpopulations. This approach allows for efficient learning of personalized models by sharing knowledge between similar tasks while preserving the unique characteristics of each subpopulation. Experimental results in simulation and case study datasets demonstrate the superior performance of the proposed method compared to several benchmarks, particularly in scenarios with high variability among subpopulations. The proposed framework not only improves prediction accuracy but also enhances interpretability by revealing underlying patterns that contribute to the personalization of models.