DIVER-0让脑电模型适应任意电极布局，提升跨数据集泛化能力。
DIVER-0 : A Fully Channel Equivariant EEG Foundation Model
- 采用全时空注意力+旋转位置编码，精准建模脑电信号动态
- 仅用10%预训练数据即达竞争力表现，通道排列下结果稳定
- 新设计的滑动时序条件位置编码支持任意电极配置适配
脑电图（EEG）在脑机接口和临床中广泛应用，但现有脑电基础模型难以建模时空脑活动，且缺乏通道排列等变性，导致在不同电极配置下泛化能力差。为此，我们提出DIVER-0，一种全新的脑电基础模型，证明了全时空注意力——而非分离的空间或时间处理——在合理设计下可实现更优性能。通过引入旋转位置编码（RoPE）建模时间关系，以及二值注意力偏置实现通道区分。同时提出滑动时序条件位置编码（STCPE），在保持时间平移等变性和通道排列等变性的前提下，优于现有条件位置编码方法，使模型能稳健适应预训练中未见的任意电极配置。实验表明，DIVER-0仅需10%预训练数据即可达到竞争力表现，且在所有通道排列条件下结果一致，验证了其跨数据集泛化能力，并确立了应对神经记录装置固有异质性的关键设计原则。
原文摘要 · Abstract (English)
Electroencephalography (EEG) is a non-invasive technique widely used in brain-computer interfaces and clinical applications, yet existing EEG foundation models face limitations in modeling spatio-temporal brain dynamics and lack channel permutation equivariance, preventing robust generalization across diverse electrode configurations. To address these challenges, we propose DIVER-0, a novel EEG foundation model that demonstrates how full spatio-temporal attention-rather than segregated spatial or temporal processing-achieves superior performance when properly designed with Rotary Position Embedding (RoPE) for temporal relationships and binary attention biases for channel differentiation. We also introduce Sliding Temporal Conditional Positional Encoding (STCPE), which improves upon existing conditional positional encoding approaches by maintaining both temporal translation equivariance and channel permutation equivariance, enabling robust adaptation to arbitrary electrode configurations unseen during pretraining. Experimental results demonstrate that DIVER-0 achieves competitive performance with only 10% of pretraining data while maintaining consistent results across all channel permutation conditions, validating its effectiveness for cross-dataset generalization and establishing key design principles for handling the inherent heterogeneity of neural recording setups.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。