Heterogeneous Multi-task Learning with Expert Diversity

TL;DR

This paper introduces MMoEEx, a novel multi-task learning model designed to improve predictions across heterogeneous biological and medical targets by increasing expert diversity and balancing task optimization.

Contribution

The paper proposes a new approach that enhances expert diversity and employs a two-step optimization to better handle heterogeneous multi-task learning scenarios.

Findings

Improved performance on MIMIC-III and PCBA datasets.

Enhanced expert diversity leads to better task-specific representations.

Effective balancing of tasks at the gradient level improves learning stability.

Abstract

Predicting multiple heterogeneous biological and medical targets is a challenge for traditional deep learning models. In contrast to single-task learning, in which a separate model is trained for each target, multi-task learning (MTL) optimizes a single model to predict multiple related targets simultaneously. To address this challenge, we propose the Multi-gate Mixture-of-Experts with Exclusivity (MMoEEx). Our work aims to tackle the heterogeneous MTL setting, in which the same model optimizes multiple tasks with different characteristics. Such a scenario can overwhelm current MTL approaches due to the challenges in balancing shared and task-specific representations and the need to optimize tasks with competing optimization paths. Our method makes two key contributions: first, we introduce an approach to induce more diversity among experts, thus creating representations more suitable for highly imbalanced and heterogenous MTL learning; second, we adopt a two-step optimization [6, 11] approach to balancing the tasks at the gradient level. We validate our method on three MTL benchmark datasets, including Medical Information Mart for Intensive Care (MIMIC-III) and PubChem BioAssay (PCBA).