Geometry-Aware Deep Congruence Networks for Manifold Learning in Cross-Subject Motor Imagery
By: Sanjeev Manivannan, Chandrashekar Lakshminarayan
Potential Business Impact:
Lets computers understand brain signals from anyone.
Cross-subject motor-imagery decoding remains a major challenge in EEG-based brain-computer interfaces due to strong subject variability and the curved geometry of covariance matrices on the symmetric positive definite (SPD) manifold. We address the zero-shot cross-subject setting, where no target-subject labels or adaptation are allowed, by introducing novel geometry-aware preprocessing modules and deep congruence networks that operate directly on SPD covariance matrices. Our preprocessing modules, DCR and RiFU, extend Riemannian Alignment by improving action separation while reducing subject-specific distortions. We further propose two manifold classifiers, SPD-DCNet and RiFUNet, which use hierarchical congruence transforms to learn discriminative, subject-invariant covariance representations. On the BCI-IV 2a benchmark, our framework improves cross-subject accuracy by 3-4% over the strongest classical baselines, demonstrating the value of geometry-aware transformations for robust EEG decoding.
Similar Papers
ManifoldFormer: Geometric Deep Learning for Neural Dynamics on Riemannian Manifolds
Machine Learning (CS)
Helps brain signals show patterns better.
SPD Learning for Covariance-Based Neuroimaging Analysis: Perspectives, Methods, and Challenges
Machine Learning (CS)
Helps computers understand brain signals better.
Cross-Subject and Cross-Montage EEG Transfer Learning via Individual Tangent Space Alignment and Spatial-Riemannian Feature Fusion
Machine Learning (CS)
Helps brain-computers learn faster for music therapy.