MSBraM：用于分层脑电动力学学习的多尺度自监督脑基础模型
MSBraM: A Multi-scale Self-supervised Brain Foundation Model for Hierarchical EEG Dynamics Learning
浏览论文内容
中文总结 AI 辅助
针对现有方法难捕捉EEG信号多尺度时间结构的问题，提出MSBraM模型。该模型采用两阶段预训练框架，经多尺度神经分词器和课程多尺度掩码策略学习分层EEG表征。实验显示其在多个下游任务中性能优越，证明显式建模多尺度时间动态对EEG基础模型的重要性。
中文摘要 AI 辅助
自监督基础模型在基于脑电图（EEG）的分析中显示出强大潜力。然而，现有方法难以捕捉EEG信号固有的多尺度时间结构，限制了跨尺度表征学习和跨下游任务的泛化。为此提出MSBraM，一种多尺度自监督脑基础模型。它采用两阶段预训练框架，先通过多尺度神经分词器将原始EEG信号离散为不同时间分辨率的语义代码，再用课程多尺度掩码策略预训练模型预测掩码代码。在超2400小时EEG数据上预训练并在12个公共数据集的10个下游任务上评估，结果表明MSBraM性能优于其他模型，证明显式建模多尺度时间动态对有效EEG基础模型至关重要。
英文摘要
Self-supervised foundation models have recently shown strong potential for electroencephalogram (EEG)-based analysis. However, existing approaches struggle to capture the inherently multi-scale temporal structure of EEG signals, where local neural patterns and long-range dependencies jointly encode task-relevant information. This limitation hampers cross-scale representation learning and generalization across diverse downstream tasks. To address this challenge, we propose MSBraM, a Multi-Scale self-supervised Brain foundation Model designed to learn hierarchical EEG representations. MSBraM follows a two-stage pretraining framework. First, a multi-scale neural tokenizer discretizes raw EEG signals into semantic codes at different temporal resolutions via vector-quantized reconstruction. Second, the model is pretrained to predict masked codes using a curriculum multi-scale masking strategy, progressively integrating fine-grained local patterns with global temporal context. We pretrain MSBraM on over 2,400 hours of EEG data and evaluate it across 10 downstream tasks on 12 public datasets. Extensive experiments show that MSBraM achieves superior performance on other state-of-the-art pretrained models, demonstrating strong generalization and transferability. These results indicate that explicitly modeling multi-scale temporal dynamics is critical for effective EEG foundation models.
发表机构
- Hunan University（湖南大学）
机构由 AI 辅助整理，请以论文原文为准。
