Guardado en:
Detalles Bibliográficos
Autores principales: Gong, Haoliang, She, Qingshan, Xu, Jiale, Gao, Yunyan, Xi, Xugang
Formato: Preprint
Publicado: 2026
Materias:
Acceso en línea:https://arxiv.org/abs/2605.26624
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866910263336239104
author Gong, Haoliang
She, Qingshan
Xu, Jiale
Gao, Yunyan
Xi, Xugang
author_facet Gong, Haoliang
She, Qingshan
Xu, Jiale
Gao, Yunyan
Xi, Xugang
contents Electroencephalogram (EEG)-based emotion recognition is an important affective computing task, and recent EEG foundation models provide useful generic representations for downstream adaptation. However, under the fine-tuning setting, three limitations remain prominent: insufficient modeling of multi-scale emotional dynamics, inadequate exploitation of inter-channel functional connectivity, and the limited expressive power of simple linear classification heads. To address these issues, this paper proposes a new EEG emotion recognition method, termed MSCGC-KAN, which introduces a structured task head composed of multi-scale causal graph convolution and Kolmogorov--Arnold feature mapping. Built on a pre-trained CBraMod backbone, MSCGC-KAN enhances downstream adaptation by jointly strengthening multi-scale temporal modeling, learnable inter-channel connectivity modeling, and nonlinear discriminative mapping within a compact task-specific head. This design preserves the representation advantage of the foundation model while making the classifier more sensitive to emotion-related spatiotemporal patterns. Extensive experiments are conducted on the public FACED and SEED-VII datasets. The proposed method achieves a balanced accuracy of 60.66\%, a Cohen's Kappa of 0.5525, and a weighted F1-score of 60.40\% on FACED, and obtains 33.27\%, 0.2223, and 33.64\%, respectively, on SEED-VII. Compared with the CBraMod+Linear baseline, the balanced accuracy is improved by 5.91 and 2.03 percentage points on the two datasets, respectively. These results indicate that structured task-head design is an effective way to improve EEG emotion recognition when fine-tuning pre-trained EEG models.
format Preprint
id arxiv_https___arxiv_org_abs_2605_26624
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle MSCGC-KAN: Multi-scale Causal Graph Convolution and Kolmogorov-Arnold Feature Mapping for EEG Emotion Recognition
Gong, Haoliang
She, Qingshan
Xu, Jiale
Gao, Yunyan
Xi, Xugang
Computer Vision and Pattern Recognition
Electroencephalogram (EEG)-based emotion recognition is an important affective computing task, and recent EEG foundation models provide useful generic representations for downstream adaptation. However, under the fine-tuning setting, three limitations remain prominent: insufficient modeling of multi-scale emotional dynamics, inadequate exploitation of inter-channel functional connectivity, and the limited expressive power of simple linear classification heads. To address these issues, this paper proposes a new EEG emotion recognition method, termed MSCGC-KAN, which introduces a structured task head composed of multi-scale causal graph convolution and Kolmogorov--Arnold feature mapping. Built on a pre-trained CBraMod backbone, MSCGC-KAN enhances downstream adaptation by jointly strengthening multi-scale temporal modeling, learnable inter-channel connectivity modeling, and nonlinear discriminative mapping within a compact task-specific head. This design preserves the representation advantage of the foundation model while making the classifier more sensitive to emotion-related spatiotemporal patterns. Extensive experiments are conducted on the public FACED and SEED-VII datasets. The proposed method achieves a balanced accuracy of 60.66\%, a Cohen's Kappa of 0.5525, and a weighted F1-score of 60.40\% on FACED, and obtains 33.27\%, 0.2223, and 33.64\%, respectively, on SEED-VII. Compared with the CBraMod+Linear baseline, the balanced accuracy is improved by 5.91 and 2.03 percentage points on the two datasets, respectively. These results indicate that structured task-head design is an effective way to improve EEG emotion recognition when fine-tuning pre-trained EEG models.
title MSCGC-KAN: Multi-scale Causal Graph Convolution and Kolmogorov-Arnold Feature Mapping for EEG Emotion Recognition
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2605.26624