When to Use Multi-Task Learning vs Intermediate Fine-Tuning for Pre-Trained Encoder Transfer Learning

TL;DR

This paper compares three transfer learning strategies in NLP, revealing a simple heuristic for choosing between them based on dataset sizes, and demonstrating the superiority of pairwise multi-task learning in most cases.

Contribution

It provides a comprehensive analysis of transfer learning methods on GLUE, introducing a heuristic for method selection based on dataset size, and empirically validating this approach.

Findings

Pairwise MTL outperforms STILTs when the target task has fewer instances than the supporting task.

The heuristic applies in over 92% of cases on GLUE.

MTL-ALL generally performs worse than pairwise methods.

Abstract

Transfer learning (TL) in natural language processing (NLP) has seen a surge of interest in recent years, as pre-trained models have shown an impressive ability to transfer to novel tasks. Three main strategies have emerged for making use of multiple supervised datasets during fine-tuning: training on an intermediate task before training on the target task (STILTs), using multi-task learning (MTL) to train jointly on a supplementary task and the target task (pairwise MTL), or simply using MTL to train jointly on all available datasets (MTL-ALL). In this work, we compare all three TL methods in a comprehensive analysis on the GLUE dataset suite. We find that there is a simple heuristic for when to use one of these techniques over the other: pairwise MTL is better than STILTs when the target task has fewer instances than the supporting task and vice versa. We show that this holds true in more than 92% of applicable cases on the GLUE dataset and validate this hypothesis with experiments varying dataset size. The simplicity and effectiveness of this heuristic is surprising and warrants additional exploration by the TL community. Furthermore, we find that MTL-ALL is worse than the pairwise methods in almost every case. We hope this study will aid others as they choose between TL methods for NLP tasks.