analiza aiqbench
This research introduces SleepDIFFormer, a multi-channel differential transformer designed to improve the generalization of sleep stage classification across heterogeneous EEG and EOG datasets. By employing cross-domain alignment and feature distribution techniques, the model addresses non-stationarity issues common in clinical configurations while maintaining interpretability through attention weight analysis. The study demonstrates superior performance on diverse benchmarks, offering a robust framework for automated diagnosis of sleep disorders without relying on manual inspection.
Sleep Stage Classification across Heterogeneous EEG/EOG Channels with Multi-Channel Differential Transformer
arXiv:2508.15215v4 Announce Type: replace Abstract: Classification of sleep stages is essential for assessing sleep quality and diagnosing sleep disorders. However, manual inspection of EEG characteristics for each stage is time-consuming and prone to human error. Although machine learning and deep learning methods have been actively developed, they continue to face challenges arising from the non-stationarity and variability of electroencephalography (EEG) and electrooculography (EOG) signals across diverse clinical configurations, often resulting in poor generalization. In this work, we propose SleepDIFFormer, a multi-channel differential transformer framework for heterogeneous EEG-EOG representation learning. SleepDIFFormer is trained across multiple sleep staging datasets, each treated as a source domain, with the goal of generalizing to unseen target domains. Specifically, it employs a Multi-channel Differential Transformer Architecture (MDTA) designed to process raw EEG and EOG signals while incorporating cross-domain alignment. Our approach mitigates spatial and temporal attention noise and learns a domain-invariant EEG-EOG representation through feature distribution alignment across datasets, thereby enhancing generalization to new domains. Empirically, we evaluated SleepDIFFormer on five diverse sleep staging datasets under domain generalization settings and benchmarked it against existing approaches, achieving superior performance. Furthermore, comprehensive ablation analyses and interpretation of the differential attention weights demonstrated their relevance to learning discriminative sleep EEG representations. These findings support the development of more generalizable approaches to automated sleep-stage classification. Our source code and checkpoint are made publicly available at https://github.com/Ben1001409/SleepDIFFormer
Abstract:Classification of sleep stages is essential for assessing sleep quality and diagnosing sleep disorders. However, manual inspection of EEG characteristics for each stage is time-consuming and prone to human error. Although machine learning and deep learning methods have been actively developed, they continue to face challenges arising from the non-stationarity and variability of electroencephalography (EEG) and electrooculography (EOG) signals across diverse clinical configurations, often resulting in poor generalization. In this work, we propose SleepDIFFormer, a multi-channel differential transformer framework for heterogeneous EEG-EOG representation learning. SleepDIFFormer is trained across multiple sleep staging datasets, each treated as a source domain, with the goal of generalizing to unseen target domains. Specifically, it employs a Multi-channel Differential Transformer Architecture (MDTA) designed to process raw EEG and EOG signals while incorporating cross-domain alignment. Our approach mitigates spatial and temporal attention noise and learns a domain-invariant EEG-EOG representation through feature distribution alignment across datasets, thereby enhancing generalization to new domains. Empirically, we evaluated SleepDIFFormer on five diverse sleep staging datasets under domain generalization settings and benchmarked it against existing approaches, achieving superior performance. Furthermore, comprehensive ablation analyses and interpretation of the differential attention weights demonstrated their relevance to learning discriminative sleep EEG representations. These findings support the development of more generalizable approaches to automated sleep-stage classification. Our source code and checkpoint are made publicly available at this https URL
SleepDIFFormer 23 Pages. Accepted by Cognitive Neurodynamics, 2026. DOI: https://doi.org/10.1007/s11571-026-10574-5
Machine Learning (cs.LG)
arXiv:2508.15215 [cs.LG]
(or arXiv:2508.15215v4 [cs.LG] for this version)
https://doi.org/10.48550/arXiv.2508.15215 Focus to learn more arXiv-issued DOI via DataCite
https://doi.org/10.1007/s11571-026-10574-5 Focus to learn more DOI(s) linking to related resources
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 335 cuvinte
Subiecte conexe
Are Heterogeneous Graph Neural Networks Truly Effective for Node Classification? A Causal Perspective
arXiv · 20 iul. 2026
HERMES: Heterogeneous Edge-Relational Multi-Head Embedded SSM Attention for Traffic Conflict Prediction at Signalized Intersections
arXiv · 24 iul. 2026
One Round Is All You Need: Analytic Federated Learning for Task-Heterogeneous Multi-Label Medical Image Classification
arXiv · 24 iul. 2026
ChorusTIC: Training-Free Multivariate Time Series Classification via Chorus In-Context Learning
arXiv · 27 aug. 2026