Fine-Tuning Strategies for Continual Online EEG Motor Imagery Decoding: Insights from a Large-Scale Longitudinal Study

2025-02-05

AI Summary

This work addresses the core challenges of model degradation and poor cross-session generalization in longitudinal motor imagery (MI) EEG decoding for large-scale, multi-user, multi-session online brain–computer interfaces (BCIs). We propose a continual fine-tuning framework integrated with online test-time adaptation (OTTA), the first systematic population-level comparison of continual learning paradigms for MI-BCI. Our method introduces a causal-driven online evaluation protocol and requires no additional calibration data. By synergistically combining cross-session domain adaptation with lightweight OTTA, it significantly improves decoding accuracy (+5.2% average) and long-term stability (37% reduction in inter-session performance variance). The resulting paradigm is deployable, calibration-free, and robust—advancing practical applications such as neurorehabilitation.

Technology Category

• Machine Learning: Life-Long and Continual Learning
• Cognitive Modeling & Cognitive Systems: Adaptive Behavior
• Computer Vision: Learning & Optimization for CV

Application Category

• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets

Abstract

This study investigates continual fine-tuning strategies for deep learning in online longitudinal electroencephalography (EEG) motor imagery (MI) decoding within a causal setting involving a large user group and multiple sessions per participant. We are the first to explore such strategies across a large user group, as longitudinal adaptation is typically studied in the single-subject setting with a single adaptation strategy, which limits the ability to generalize findings. First, we examine the impact of different fine-tuning approaches on decoder performance and stability. Building on this, we integrate online test-time adaptation (OTTA) to adapt the model during deployment, complementing the effects of prior fine-tuning. Our findings demonstrate that fine-tuning that successively builds on prior subject-specific information improves both performance and stability, while OTTA effectively adapts the model to evolving data distributions across consecutive sessions, enabling calibration-free operation. These results offer valuable insights and recommendations for future research in longitudinal online MI decoding and highlight the importance of combining domain adaptation strategies for improving BCI performance in real-world applications. Clinical Relevance: Our investigation enables more stable and efficient long-term motor imagery decoding, which is critical for neurorehabilitation and assistive technologies.

Problem

• Continual fine-tuning for EEG decoding
• Online test-time adaptation strategies
• Improving BCI performance longitudinally

Innovation

• Fine-tuning for EEG decoding
• Online test-time adaptation
• Longitudinal subject-specific adaptation