Towards Unified Multi-task EEG Analysis with Low-Rank Adaptation

TL;DR

This paper introduces MTEEG, a multi-task EEG analysis framework using low-rank adaptation modules to enable simultaneous task adaptation, reducing costs and improving performance over single-task models.

Contribution

The study proposes a novel multi-task EEG analysis method with task-specific low-rank modules, addressing conflicts and enhancing multi-task learning capabilities.

Findings

MTEEG surpasses state-of-the-art single-task methods on most metrics.

Three variants of MTEEG effectively balance task specificity and interaction.

Demonstrates potential for general-purpose brain-computer interfaces.

Abstract

Recent self-supervised pre-training methods for electroencephalogram (EEG) have shown promising results. However, the pre-trained models typically require full fine-tuning on each downstream task individually to achieve good performance. In practical applications involving multiple tasks, utilizing a separate model for each task is not ideal regarding computational and spatial cost. In this study, we go one step further and explore the simultaneous adaptation of a pre-trained model to multiple different tasks. The EEG signals exhibit significant heterogeneity due to their collection from various subjects using diverse devices and experimental setups, resulting in potential conflicts among different tasks that impede joint optimization. To tackle this challenge, we propose MTEEG, a multi-task EEG analysis framework which incorporates task-specific low-rank adaptation (LoRA) modules to disentangle the parameter space and alleviate task conflicts. To investigate the trade-off between task specification and interaction, we propose three variants of MTEEG that integrate the LoRA modules in different ways and evaluate them on six downstream tasks, demonstrating that MTEEG can surpass state-of-the-art single-task methods on the majority of metrics. MTEEG shows the potential of multi-task EEG analysis and promotes the development of general-purpose brain-computer interfaces in the future.