HEEGNet: Hyperbolic Embeddings for EEG

2026-01-06

arXiv.org

AI Summary

This work addresses the degradation of generalization performance in electroencephalography (EEG) decoding under distribution shifts, such as those encountered in cross-subject scenarios. To this end, the authors propose HEEGNet, a hybrid neural architecture that integrates Euclidean and hyperbolic geometries. The study provides the first empirical evidence that EEG data inherently exhibit hyperbolic geometric structure, and leverages this insight by jointly modeling hierarchical relationships within the signals. A coarse-to-fine domain adaptation strategy is introduced to learn domain-invariant hyperbolic embeddings. Extensive experiments on multiple public EEG datasets demonstrate that HEEGNet achieves state-of-the-art performance in tasks including visual evoked potential decoding and emotion recognition, significantly enhancing cross-domain generalization capabilities.

Technology Category

• Machine Learning: Transfer, Domain Adaptation, Multi-Task Learning
• Cognitive Modeling & Cognitive Systems: Neural Spike Coding
• Natural Language Processing: Learning & Optimization for NLP

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Economics, Online Markets and Human Computation: Incentives in network design for Web infrastructures and ecosystems
• Web Mining and Content Analysis: Large pretrained models with web data

Abstract

Electroencephalography (EEG)-based brain-computer interfaces facilitate direct communication with a computer, enabling promising applications in human-computer interactions. However, their utility is currently limited because EEG decoding often suffers from poor generalization due to distribution shifts across domains (e.g., subjects). Learning robust representations that capture underlying task-relevant information would mitigate these shifts and improve generalization. One promising approach is to exploit the underlying hierarchical structure in EEG, as recent studies suggest that hierarchical cognitive processes, such as visual processing, can be encoded in EEG. While many decoding methods still rely on Euclidean embeddings, recent work has begun exploring hyperbolic geometry for EEG. Hyperbolic spaces, regarded as the continuous analogue of tree structures, provide a natural geometry for representing hierarchical data. In this study, we first empirically demonstrate that EEG data exhibit hyperbolicity and show that hyperbolic embeddings improve generalization. Motivated by these findings, we propose HEEGNet, a hybrid hyperbolic network architecture to capture the hierarchical structure in EEG and learn domain-invariant hyperbolic embeddings. To this end, HEEGNet combines both Euclidean and hyperbolic encoders and employs a novel coarse-to-fine domain adaptation strategy. Extensive experiments on multiple public EEG datasets, covering visual evoked potentials, emotion recognition, and intracranial EEG, demonstrate that HEEGNet achieves state-of-the-art performance. The code is available at https://github.com/fightlesliefigt/HEEGNet

Problem

• EEG
• domain shift
• generalization
• brain-computer interface
• hierarchical structure

Innovation

• hyperbolic embeddings
• EEG decoding
• domain generalization
• hierarchical structure
• brain-computer interface