面向帕金森病刺激前后状态分类的 swap-adversarial 域泛化框架
A swap-adversarial framework for domain generalization in pre- and post-stimulation Parkinsonian state classification
AI 导读
研究者提出一种 swap-adversarial 框架，用于缓解 ECoG 数据中受试者间差异大和高维小样本问题，实现跨数据集的域泛化。框架包含稳健预处理、受试者间平衡通道交换（ISBCS）增强和域对抗学习（DAL），并发布了首个基于 6-OHDA 诱导大鼠模型长期 ECoG 记录的可复现基准，标注电刺激前后神经响应。
正文 · 原文
Abstract:We propose a novel swap-adversarial framework that mitigates high inter-subject variability and the high-dimensional low-sample-size problem in electrocorticography (ECoG) data. It achieves robust domain generalization across ECoG and electroencephalography (EEG)-based brain-computer interface datasets. Our framework integrates (1) robust preprocessing, (2) inter-subject balanced channel swap (ISBCS) for cross-subject augmentation, and (3) domain-adversarial learning (DAL) to suppress subject-specific bias. The ISBCS method is a bio-inspired channel swapping strategy that exchanges only functionally corresponding channels across subjects, guided by a brain map, to mitigate inter-subject distribution differences. The DAL strategy encourages the model to learn task-relevant shared features. In addition, we introduce a new ECoG dataset, the first reproducible benchmark, which is constructed from long-term ECoG recordings of 6-hydroxydopamine-induced rat models and annotated with neural responses measured before and after electrical stimulation. We validate the effectiveness of this framework through extensive experiments under cross-subject, cross-session, and cross-dataset settings. Our results show that the proposed framework exhibits the best and robust generalization performance both for our newly constructed ECoG and public EEG datasets.
| Subjects: | Machine Learning (cs.LG); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2602.10528 [cs.LG] |
| (or arXiv:2602.10528v3 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2602.10528 arXiv-issued DOI via DataCite |
Submission history
From: Jibum Kim [view email]
[v1]
Wed, 11 Feb 2026 04:52:46 UTC (5,918 KB)
[v2]
Tue, 30 Jun 2026 01:30:13 UTC (4,317 KB)
[v3]
Tue, 27 Oct 2026 04:24:20 UTC (4,602 KB)
来源：arXiv cs.AI · arxiv.org