Metraipolis › archive › dc_775781dadcd0
ProtoGIB-Workload: Learning Workload-Specific Neural Topology Prototypes across Subjects — arXiv:2608.10647
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.10647
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-19T06:18:45.487Z
- SHA-256 of the archived text
24b580e1c7c8485f5bd716eb2360bcda879010382624d1fac0a8418b322dcee5- Stable URL of this page
https://metraipolis.com/documento/dc_775781dadcd0
How to cite
ProtoGIB-Workload: Learning Workload-Specific Neural Topology Prototypes across Subjects — arXiv:2608.10647 — arXiv (en), https://arxiv.org/abs/2608.10647 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_775781dadcd0 (Metraipolis archive dc_775781dadcd0, sha256 24b580e1c7c8485f5bd716eb2360bcda879010382624d1fac0a8418b322dcee5)
BibTeX
@misc{dc775781dadcd0,
title = {ProtoGIB-Workload: Learning Workload-Specific Neural Topology Prototypes across Subjects — arXiv:2608.10647},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.10647},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_775781dadcd0; sha256 24b580e1c7c8485f5bd716eb2360bcda879010382624d1fac0a8418b322dcee5},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.10647. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Reliable electroencephalography (EEG)-based mental workload recognition is crucial for adaptive human-centered systems, yet practical deployment requires models to generalize to users unseen during training. Although functional connectivity graphs are widely adopted to capture workload-related neural interactions, they inherently entangle task-relevant structures with subject-specific physiological traits and sample-level noise. This entanglement often leads models to learn structural shortcuts, severely degrading cross-subject generalization. To address this, we propose ProtoGIB-Workload, a novel framework that explicitly regularizes and aligns graph structures for subject-independent workload recognition. Our approach introduces a Stochastic Graph Information Bottleneck (SGIB) to compress dense correlation priors into compact, task-relevant subgraphs, filtering out input-related redundancy. Crucially, to prevent the retention of subject-specific spurious edges, we propose a Class-Conditional Topology Stabilizer (CTS). Leveraging the fixed electrode coordinates of EEG data, CTS operates directly on graph-generation probabilities to encourage consistent edge-generation statistics across different subjects sharing the same workload class. Extensive experiments on two public EEG workload datasets and one in-house EEG cognitive load dataset of air traffic controllers under strict leave-one-subject-out (LOSO) protocols demonstrate that ProtoGIB-Workload significantly outperforms state-of-the-art temporal and graph-based baselines, improving the cross-subject Macro-F1 score by an average of 5.15% (up to 6.34%). Further analyses confirm that our method successfully extracts stable, cross-subject consistent neural connectivity patterns. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-12 in cs.HC). Categorie arXiv: Human-Computer Interaction (cs.HC). Pagina del lavoro: https://arxiv.org/abs/2608.10647 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-19T06:11:23.450Z dalla pagina https://arxiv.org/catchup/cs.HC/2026-08-12?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).