发表机构
Georgia Institute of Technology; Korea Advanced Institute of Science and Technology（佐治亚理工学院; 韩国科学技术院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对脑电癫痫检测与预测，提出HyBrain模型，用软超边替代成对边以捕捉时空耦合，在TUSZ和CHB-MIT上优于十个基线，并高效训练。
AI 中文摘要
从脑电中进行癫痫检测和预测在临床上很重要，但具有挑战性，因为癫痫发作是罕见的、时间局部的，并作为跨多个通道的协调事件传播。最近的动态图神经网络通过在每个时间步的成对通道边上运行时间模型来对此进行建模。然而，这种成对构建方式遗漏了构成癫痫发作的时空耦合，且训练成本高昂。我们提出了HyBrain，通过一小部分软超边而非成对边来总结时空脑电证据。一个每通道的Mamba骨干网络为每个（通道，秒）生成一个令牌，一个时空超边块通过软成员关系将这些令牌汇聚到E_h个共享组嵌入中，并将其广播回去。同一个编码器服务于三个下游任务：基于窗口的检测、一秒点式检测和发作前期预测。在TUSZ和CHB-MIT上，HyBrain在每一个报告设置中对比十个基线取得了最佳AUROC，在长片段发作前期预测上差距最大。它还在训练时间和峰值GPU内存上与最高效的基线相当。定性分析表明，即使是一个学习到的超边也能清晰地捕捉到真实癫痫片段上的发作前期->发作期->发作后期轨迹。
英文摘要
Seizure detection and prediction from EEG are clinically important but challenging because seizures are rare, temporally localized, and propagate as coordinated events across multiple channels. Recent dynamic graph neural networks model this by running a temporal model over a sequence of per-time-step pairwise channel edges. However, this pairwise construction misses the spatiotemporal coupling that constitutes a seizure, at substantial training cost. We propose HyBrain, which summarizes spatiotemporal EEG evidence through a small set of soft hyperedges rather than pairwise edges. A per-channel Mamba backbone produces one token per (channel, second), and a spatiotemporal hyperedge block pools these tokens into E_h shared group embeddings through soft memberships and broadcasts them back. The same encoder serves three downstream tasks: window-based detection, one-second point-wise detection, and preictal seizure prediction. On TUSZ and CHB-MIT, HyBrain achieves the best AUROC on every reported setting against ten baselines, with the largest gap on long-clip preictal prediction. It also matches the most efficient baselines in training time and peak GPU memory. A qualitative analysis shows that even a single learned hyperedge cleanly captures the preictal -> ictal -> postictal trajectory on a real seizure clip.
CommentsAccepted at CIKM 2026. 7 figures, 6 tables
