AI4Meder

AI4Meder 站内搜索

搜索医学 AI 论文与资源

按论文、数据资源、技术竞赛、投稿截止日期和课程资源检索社区内容,快速进入对应详情页。

1 条结果

输入关键词或点击标签,按论文、数据资源、竞赛截止日期、征稿与课程缩小范围。 标签:balanced signed graph 范围:论文

清空筛选
论文ICLR 2026 Poster2026 年clinical prediction

基于平衡符号图算法展开的轻量级 EEG 分类 Transformer

ICLR 2026 Poster accepted paper at ICLR 2026. Samples of brain signals collected by EEG sensors have inherent anti-correlations that are well modeled by negative edges in a finite graph. To differentiate epilepsy patients from healthy subjects using collected EEG signals, we build lightweight and interpretable transformer-like neural nets by unrolling a spectral denoising algorithm for signals on a balanced signed graph---graph with no cycles of odd number of negative edges. A balanced signed graph has well-defined frequencies that map to a corresponding positive graph via similarity transform of the graph Laplacian matrices. We implement an ideal low-pass filter efficiently on the mapped positive graph via Lanczos approximation, where the optimal cutoff frequency is learned from data.