Saved in:
Bibliographic Details
Main Authors: Ortiz-Barajas, Jesus-German, Gomez-Adorno, Helena, Solorio, Thamar
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2407.01411
Tags: Add Tag
No Tags, Be the first to tag this record!
Table of Contents:
  • We present HyperLoader, a simple approach that combines different parameter-efficient fine-tuning methods in a multi-task setting. To achieve this goal, our model uses a hypernetwork to generate the weights of these modules based on the task, the transformer layer, and its position within this layer. Our method combines the benefits of multi-task learning by capturing the structure of all tasks while reducing the task interference problem by encapsulating the task-specific knowledge in the generated weights and the benefits of combining different parameter-efficient methods to outperform full-fine tuning. We provide empirical evidence that HyperLoader outperforms previous approaches in most datasets and obtains the best average performance across tasks in high-resource and low-resource scenarios.