Geometry- and Relation-Aware Diffusion for EEG Super-Resolution

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Yao, Laura, Zhang, Gengwei, Chowdhury, Moajjem, Liu, Yunmei, Chen, Tianlong
Formato: Preprint
Publicado: 2026
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866910008894029824
author Yao, Laura
Zhang, Gengwei
Chowdhury, Moajjem
Liu, Yunmei
Chen, Tianlong
author_facet Yao, Laura
Zhang, Gengwei
Chowdhury, Moajjem
Liu, Yunmei
Chen, Tianlong
contents Recent electroencephalography (EEG) spatial super-resolution (SR) methods, while showing improved quality by either directly predicting missing signals from visible channels or adapting latent diffusion-based generative modeling to temporal data, often lack awareness of physiological spatial structure, thereby constraining spatial generation performance. To address this issue, we introduce TopoDiff, a geometry- and relation-aware diffusion model for EEG spatial super-resolution. Inspired by how human experts interpret spatial EEG patterns, TopoDiff incorporates topology-aware image embeddings derived from EEG topographic representations to provide global geometric context for spatial generation, together with a dynamic channel-relation graph that encodes inter-electrode relationships and evolves with temporal dynamics. This design yields a spatially grounded EEG spatial super-resolution framework with consistent performance improvements. Across multiple EEG datasets spanning diverse applications, including SEED/SEED-IV for emotion recognition, PhysioNet motor imagery (MI/MM), and TUSZ for seizure detection, our method achieves substantial gains in generation fidelity and leads to notable improvements in downstream EEG task performance.
format Preprint
id arxiv_https___arxiv_org_abs_2602_02238
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Geometry- and Relation-Aware Diffusion for EEG Super-Resolution
Yao, Laura
Zhang, Gengwei
Chowdhury, Moajjem
Liu, Yunmei
Chen, Tianlong
Machine Learning
Artificial Intelligence
Recent electroencephalography (EEG) spatial super-resolution (SR) methods, while showing improved quality by either directly predicting missing signals from visible channels or adapting latent diffusion-based generative modeling to temporal data, often lack awareness of physiological spatial structure, thereby constraining spatial generation performance. To address this issue, we introduce TopoDiff, a geometry- and relation-aware diffusion model for EEG spatial super-resolution. Inspired by how human experts interpret spatial EEG patterns, TopoDiff incorporates topology-aware image embeddings derived from EEG topographic representations to provide global geometric context for spatial generation, together with a dynamic channel-relation graph that encodes inter-electrode relationships and evolves with temporal dynamics. This design yields a spatially grounded EEG spatial super-resolution framework with consistent performance improvements. Across multiple EEG datasets spanning diverse applications, including SEED/SEED-IV for emotion recognition, PhysioNet motor imagery (MI/MM), and TUSZ for seizure detection, our method achieves substantial gains in generation fidelity and leads to notable improvements in downstream EEG task performance.
title Geometry- and Relation-Aware Diffusion for EEG Super-Resolution
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2602.02238