MTLoRA: A Low-Rank Adaptation Approach for Efficient Multi-Task Learning
This addresses the need for efficient adaptation of pre-trained models to multiple tasks, offering a Pareto-optimal trade-off between parameters and accuracy, though it is incremental as it builds on existing parameter-efficient methods.
The paper tackles the problem of parameter-efficient fine-tuning in multi-task learning (MTL) by introducing MTLoRA, a framework that uses low-rank adaptation modules to disentangle parameter spaces, achieving higher accuracy on downstream tasks while reducing trainable parameters by 3.6x compared to full fine-tuning.
Adapting models pre-trained on large-scale datasets to a variety of downstream tasks is a common strategy in deep learning. Consequently, parameter-efficient fine-tuning methods have emerged as a promising way to adapt pre-trained models to different tasks while training only a minimal number of parameters. While most of these methods are designed for single-task adaptation, parameter-efficient training in Multi-Task Learning (MTL) architectures is still unexplored. In this paper, we introduce MTLoRA, a novel framework for parameter-efficient training of MTL models. MTLoRA employs Task-Agnostic and Task-Specific Low-Rank Adaptation modules, which effectively disentangle the parameter space in MTL fine-tuning, thereby enabling the model to adeptly handle both task specialization and interaction within MTL contexts. We applied MTLoRA to hierarchical-transformer-based MTL architectures, adapting them to multiple downstream dense prediction tasks. Our extensive experiments on the PASCAL dataset show that MTLoRA achieves higher accuracy on downstream tasks compared to fully fine-tuning the MTL model while reducing the number of trainable parameters by 3.6x. Furthermore, MTLoRA establishes a Pareto-optimal trade-off between the number of trainable parameters and the accuracy of the downstream tasks, outperforming current state-of-the-art parameter-efficient training methods in both accuracy and efficiency. Our code is publicly available.