HyperLoader: Integrating Hypernetwork-Based LoRA and Adapter Layers into Multi-Task Transformers for Sequence Labelling

TL;DR

HyperLoader introduces a hypernetwork-based method that combines parameter-efficient fine-tuning techniques for multi-task sequence labeling, outperforming previous methods across various datasets and resource scenarios.

Contribution

It proposes a novel hypernetwork approach to integrate LoRA and adapter layers for multi-task transformers, enhancing performance and reducing task interference.

Findings

Outperforms previous methods on most datasets

Achieves best average performance in high-resource scenarios

Effective in low-resource settings

Abstract

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.