# Self-Paced Multitask Learning with Shared Knowledge

## TL;DR

This paper proposes a self-paced multitask learning framework that sequentially selects related tasks from easy to hard, improving learning efficiency and performance across various multitask learning settings.

## Contribution

It introduces a novel self-paced task selection method with a bi-convex loss function, applicable to multiple multitask learning paradigms, enhancing their effectiveness.

## Key findings

- Self-paced task selection outperforms baseline methods in all experiments.
- The approach effectively models human-like learning progression.
- Applicable to feature learning and structure optimization in multitask learning.

## Abstract

This paper introduces self-paced task selection to multitask learning, where instances from more closely related tasks are selected in a progression of easier-to-harder tasks, to emulate an effective human education strategy, but applied to multitask machine learning. We develop the mathematical foundation for the approach based on iterative selection of the most appropriate task, learning the task parameters, and updating the shared knowledge, optimizing a new bi-convex loss function. This proposed method applies quite generally, including to multitask feature learning, multitask learning with alternating structure optimization, etc. Results show that in each of the above formulations self-paced (easier-to-harder) task selection outperforms the baseline version of these methods in all the experiments.