SPERA: Spherical Prior EEG Foundation Model with Geometry- and Frequency-Aware Latent Prediction

查看原文 / View Original 编辑 / Edit

Computer Science > Machine Learning arXiv:2610.10571 (cs) [Submitted on 4 Oct 2026] Title: SPERA: Spherical Prior EEG Foundation Model with Geometry- and Frequency-Aware Latent Prediction Authors: Minsu Kim, Ye-Sung Kim, Hyeseong Jeon, Wooseok Hyung, Joshua Lee, Chang-Hwan Im.

计算机科学 > 机器学习 arXiv:2610.10571 (cs) [提交于 2026 年 10 月 4 日] 标题：SPERA：具有几何和频率感知潜在预测功能的球形先验脑电图基础模型作者：Minsu Kim, Ye-Sung Kim, Hyeseong Jeon, Wooseok Hyung, Joshua Lee, Chang-Hwan Im。

Abstract: Electroencephalography (EEG) provides a non-invasive measure of ongoing neural activity, but building general-purpose EEG models remains challenging due to the heterogeneity of subjects, devices, and electrode montages. Existing EEG foundation models predominantly rely on reconstruction-based objectives defined on the observed signal, which contains both neural and non-neural components.

摘要：脑电图（EEG）提供了一种非侵入性的持续神经活动测量方法，但由于受试者、设备和电极放置方式的异质性，构建通用脑电图模型仍然具有挑战性。现有的脑电图基础模型主要依赖于在观测信号上定义的基于重构的目标，而这些信号同时包含神经和非神经成分。

We introduce SPERA (Spherical Prior EEG Representation Architecture), an EEG foundation model that adopts the joint-embedding predictive architecture (JEPA) to predict in latent space. SPERA introduces a Legendre-polynomial spatial prior, incorporated into attention to encode varying scalp electrode geometries.

我们引入了 SPERA（球形先验脑电图表示架构），这是一种采用联合嵌入预测架构（JEPA）在潜在空间进行预测的脑电图基础模型。SPERA 引入了一种勒让德多项式空间先验，并将其整合到注意力机制中，以编码不同的头皮电极几何结构。

Two further components adapt the model to EEG: factorized temporal and spatial attention interleaved with periodic full-attention blocks, and a relational spectral regularizer aligning latent similarity structure with spectral views. Pretrained on approximately 80,000 hours of EEG from 29,048 subjects across 106 datasets, SPERA achieves the highest average balanced accuracy across nine downstream tasks spanning clinical, cognitive, and BCI applications.

另外两个组件使模型能够适应脑电图：与周期性全注意力块交错的因子化时空注意力，以及将潜在相似性结构与频谱视图对齐的关系谱正则化器。SPERA 在来自 106 个数据集、29,048 名受试者的约 80,000 小时脑电图数据上进行了预训练，在涵盖临床、认知和脑机接口（BCI）应用的九项下游任务中实现了最高的平均平衡准确率。

SPERA further exhibits strong parameter efficiency under linear probing and robustness across varying recording conditions, suggesting its potential as a general-purpose backbone for diverse EEG analyses.

SPERA 在线性探测下表现出强大的参数效率，并在不同的记录条件下展现出鲁棒性，这表明它有潜力成为各种脑电图分析的通用骨干模型。