CRCC: Contrast-Based Robust Cross-Subject and Cross-Site Representation Learning for EEG
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866911461443371008 |
|---|---|
| author | Wong, Xiaobin Zhao, Zhonghua Guo, Haoran Liu, Zhengyi Wu, Yu Yan, Feng Wang, Zhiren Song, Sen |
| author_facet | Wong, Xiaobin Zhao, Zhonghua Guo, Haoran Liu, Zhengyi Wu, Yu Yan, Feng Wang, Zhiren Song, Sen |
| contents | EEG-based neural decoding models often fail to generalize across acquisition sites due to structured, site-dependent biases implicitly exploited during training. We reformulate cross-site clinical EEG learning as a bias-factorized generalization problem, in which domain shifts arise from multiple interacting sources. We identify three fundamental bias factors and propose a general training framework that mitigates their influence through data standardization and representation-level constraints. We construct a standardized multi-site EEG benchmark for Major Depressive Disorder and introduce CRCC, a two-stage training paradigm combining encoder-decoder pretraining with joint fine-tuning via cross-subject/site contrastive learning and site-adversarial optimization. CRCC consistently outperforms state-of-the-art baselines and achieves a 10.7 percentage-point improvement in balanced accuracy under strict zero-shot site transfer, demonstrating robust generalization to unseen environments. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_19138 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | CRCC: Contrast-Based Robust Cross-Subject and Cross-Site Representation Learning for EEG Wong, Xiaobin Zhao, Zhonghua Guo, Haoran Liu, Zhengyi Wu, Yu Yan, Feng Wang, Zhiren Song, Sen Neurons and Cognition Artificial Intelligence EEG-based neural decoding models often fail to generalize across acquisition sites due to structured, site-dependent biases implicitly exploited during training. We reformulate cross-site clinical EEG learning as a bias-factorized generalization problem, in which domain shifts arise from multiple interacting sources. We identify three fundamental bias factors and propose a general training framework that mitigates their influence through data standardization and representation-level constraints. We construct a standardized multi-site EEG benchmark for Major Depressive Disorder and introduce CRCC, a two-stage training paradigm combining encoder-decoder pretraining with joint fine-tuning via cross-subject/site contrastive learning and site-adversarial optimization. CRCC consistently outperforms state-of-the-art baselines and achieves a 10.7 percentage-point improvement in balanced accuracy under strict zero-shot site transfer, demonstrating robust generalization to unseen environments. |
| title | CRCC: Contrast-Based Robust Cross-Subject and Cross-Site Representation Learning for EEG |
| topic | Neurons and Cognition Artificial Intelligence |
| url | https://arxiv.org/abs/2602.19138 |