RECTOR: Masked Region-Channel-Temporal Modeling for Affective and Cognitive Representation Learning
arXiv:2606.15278v1 Announce Type: cross Abstract: Affective and cognitive disorders manifest as distributed, time-varying brain network dynamics across regions, channels, and time, challenging robust representation learning from EEG/sEEG for clinical diagnosis. We propose RECTOR (Masked Region-Channel-Temporal Modeling), an end-to-end self-supervised framework that unifies joint region-channel-temporal representation learning beyond fixed anatomical priors. At its core, RECTOR-SA is a hierarchical, block-sparse self-attention induced by Adaptive Functional Partitioning that evolves region stru
Advances in self-supervised learning and increasing computational power allow for more sophisticated models to process complex, multi-modal biological data from brain activity.
This research could lead to more accurate and earlier diagnosis of affective and cognitive disorders by providing robust, data-driven representations of brain dynamics, reducing reliance on subjective clinical assessments.
The ability to learn representations directly from raw region-channel-temporal data without fixed anatomical priors offers a new pathway for understanding brain disorders and developing targeted interventions.
- · Neuroscience researchers
- · Medical technology companies (EEG/sEEG)
- · Pharmaceutical companies (drug discovery)
- · Patients with affective/cognitive disorders
- · Traditional diagnostic methods
Improved early detection and differential diagnosis of conditions like depression, anxiety, and Alzheimer's.
Accelerated development of personalized therapeutic interventions based on objective, data-driven disease markers.
Enhanced understanding of brain function leading to new theories of consciousness and cognitive processing.
This signal links to a primary source. Continuum Brief monitors and indexes it as part of the live intelligence stream — we do not republish source content.
Read at arXiv cs.AI