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

TL;DR

TopoDiff is a novel EEG super-resolution model that incorporates spatial topology and electrode relations, significantly improving generation quality and downstream task performance across various EEG datasets.

Contribution

We introduce TopoDiff, a geometry- and relation-aware diffusion model that integrates topographic embeddings and dynamic electrode relations for enhanced EEG super-resolution.

Findings

Achieves substantial fidelity improvements in EEG spatial super-resolution.

Enhances downstream EEG task performance such as emotion recognition and seizure detection.

Demonstrates consistent gains across multiple diverse EEG datasets.

Abstract

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.