Learning from Brain Topography: A Hierarchical Local-Global Graph-Transformer Network for EEG Emotion Recognition

TL;DR

This paper introduces Neuro-HGLN, a hierarchical graph-transformer network that models local and global brain interactions for improved EEG emotion recognition, integrating neurophysiological priors and advanced graph learning.

Contribution

The paper presents a novel neurophysiologically grounded hierarchical graph-transformer architecture that captures local topological and global functional brain dependencies for EEG analysis.

Findings

Achieves state-of-the-art results on multiple EEG emotion recognition benchmarks.

Effectively models local electrode relationships and global brain connectivity.

Provides interpretable insights aligned with neurophysiological structures.

Abstract

Understanding how local neurophysiological patterns interact with global brain dynamics is essential for decoding human emotions from EEG signals. However, existing deep learning approaches often overlook the brain's intrinsic spatial organization, failing to simultaneously capture local topological relations and global dependencies. To address these challenges, we propose Neuro-HGLN, a Neurologically-informed Hierarchical Graph-Transformer Learning Network that integrates biologically grounded priors with hierarchical representation learning. Neuro-HGLN first constructs a spatial Euclidean prior graph based on physical electrode distances to serve as an anatomically grounded inductive bias. A learnable global dynamic graph is then introduced to model functional connectivity across the entire brain. In parallel, to capture fine-grained regional dependencies, Neuro-HGLN builds region-level local graphs using a multi-head self-attention mechanism. These graphs are processed synchronously through local-constrained parallel GCN layers to produce region-specific representations. Subsequently, an iTransformer encoder aggregates these features to capture cross-region dependencies under a dimension-as-token formulation. Extensive experiments demonstrate that Neuro-HGLN achieves state-of-the-art performance on multiple benchmarks, providing enhanced interpretability grounded in neurophysiological structure. These results highlight the efficacy of unifying local topological learning with cross-region dependency modeling for robust EEG emotion recognition.