{"ID":2850238,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2510.22197","arxiv_id":"2510.22197","title":"Multi-dataset Joint Pre-training of Emotional EEG Enables Generalizable Affective Computing","abstract":"Task-specific pre-training is essential when task representations diverge from generic pre-training features. Existing task-general pre-training EEG models struggle with complex tasks like emotion recognition due to mismatches between task-specific features and broad pre-training approaches. This work aims to develop a task-specific multi-dataset joint pre-training framework for cross-dataset emotion recognition, tackling problems of large inter-dataset distribution shifts, inconsistent emotion category definitions, and substantial inter-subject variability. We introduce a cross-dataset covariance alignment loss to align second-order statistical properties across datasets, enabling robust generalization without the need for extensive labels or per-subject calibration. To capture the long-term dependency and complex dynamics of EEG, we propose a hybrid encoder combining a Mamba-like linear attention channel encoder and a spatiotemporal dynamics model. Our method outperforms state-of-the-art large-scale EEG models by an average of 4.57% in AUROC for few-shot emotion recognition and 11.92% in accuracy for zero-shot generalization to a new dataset. Performance scales with the increase of datasets used in pre-training. Multi-dataset joint pre-training achieves a performance gain of 8.55% over single-dataset training. This work provides a scalable framework for task-specific pre-training and highlights its benefit in generalizable affective computing. Our code is available at https://github.com/ncclab-sustech/mdJPT_nips2025.","short_abstract":"Task-specific pre-training is essential when task representations diverge from generic pre-training features. Existing task-general pre-training EEG models struggle with complex tasks like emotion recognition due to mismatches between task-specific features and broad pre-training approaches. This work aims to develop a...","url_abs":"https://arxiv.org/abs/2510.22197","url_pdf":"https://arxiv.org/pdf/2510.22197v1","authors":"[\"Qingzhu Zhang\",\"Jiani Zhong\",\"Zongsheng Li\",\"Xinke Shen\",\"Quanying Liu\"]","published":"2025-10-25T07:30:24Z","proceeding":"cs.LG","tasks":"[\"cs.LG\",\"cs.AI\",\"q-bio.NC\"]","methods":"[]","has_code":false,"code_links":[{"ID":607778,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2850238,"paper_url":"https://arxiv.org/abs/2510.22197","paper_title":"Multi-dataset Joint Pre-training of Emotional EEG Enables Generalizable Affective Computing","repo_url":"https://github.com/ncclab-sustech/mdJPT_nips2025","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}