arXiv cs.LG + cs.RO + cs.HC· Ying Zhou, Mengting Liu·· 3 天前AI 评分43
GRAFT-EEG 提出跨数据集运动想象 EEG 的规范感知物理场迁移方法
GRAFT-EEG: Gauge-Aware Physical Field Transport for Cross-Dataset Motor-Imagery EEG
AI 导读
GRAFT-EEG 用规范感知物理场迁移做跨数据集运动想象 EEG 解码，在 5 个留一数据集目标、253 名受试者上取得 60.865% 等目标平衡准确率，比 strict-clean 5/5 BIOT 的 52.684% 高 8.182 个百分点。
正文 · 原文
Abstract:Cross-dataset EEG decoding often treats montage, reference, and active-sensor changes as representation shift, although they also alter the observation operator. We study target-statistics-blind transfer: fitting receives no target signal, label, or empirical statistic, and electrode coordinates only instantiate a fixed prediction operator. method removes the active-set common-reference gauge and transports each native mask through a template motor leadfield. A source-fitted spectral classifier anchors the decision; a bounded state-space-model (SSM) residual is secondary. We establish restricted identifiability and an operator-perturbation bound. Across five leave-one-dataset-out targets (253 participants), dynamic method achieved 60.865% equal-target balanced accuracy versus 52.684% for strict-clean 5/5 BIOT (hierarchical difference +8.182 points; 95% CI +6.382 to +10.196; positive in every target). On four EEGPT-clean targets, the descriptive means were 61.520% and 59.057%. In four post-hoc exact same-parent tests, FULL exceeded coordinate-basis, matched-spectrum, row-shuffled, and wrong-anatomy controls by 9.959, 9.698, 11.241, and 3.985 points, respectively (all 95% CIs excluded zero; Holm-adjusted P<0.001). A separate 60-participant same-paradigm evaluation retained a positive physical-operator contrast (+4.029 points; +2.338 to +5.773), whereas dynamic--static was inconclusive; its preregistered status is partial confirmation rather than unrestricted external validation. The SSM added +1.059 points (+0.013 to +1.892). Claims remain bounded to five binary motor-imagery domains and the tested operators.
| Comments: | Under review at ICLR 2027 |
| Subjects: | Machine Learning (cs.LG); Signal Processing (eess.SP) |
| Cite as: | arXiv:2610.23620 [cs.LG] |
| (or arXiv:2610.23620v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2610.23620 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Ying Zhou [view email]
[v1]
Fri, 16 Oct 2026 15:30:37 UTC (3,875 KB)
来源：arXiv cs.LG + cs.RO + cs.HC · arxiv.org