Learning aligned EEG representations with subject-specific encoders
cs.LG, cs.AI
Submitted: 2026-06-15
Updated: 2026-09-15
Code: https://github.com/brunaafl/LatentHybrid
License: http://creativecommons.org/licenses/by/4.0/
The gist: Cross-subject EEG decoding promises more training data, but it also exposes neural networks to strong inter-subject distribution shifts.
Terminology
Abstract
Cross-subject EEG decoding promises more training data, but it also exposes neural networks to strong inter-subject distribution shifts. We study whether task supervision and architecture alone can learn subject-aligned representations. We replace a shared EEG encoder with subject-specific encoders followed by a common classifier, and compare this hybrid model with standard EEGNet, AttentionBaseNet, and CTNet baselines with Euclidean Alignment (EA) on three motor-imagery datasets and one motor-execution dataset. EA improves shared encoders by recentering subject covariances, whereas the hybrid encoder reduces reliance on EA: removing EA has little effect on validation-loss dynamics or latent-space organization, and both hybrid variants consistently outperform non-aligned shared baselines. Subject-specific heads increase class distinctiveness and place each subject close to its own latent manifold while improving within-subject class separation. However, on cross-subject classification, subject-specific heads hinder direct parameter transfer to unseen subjects, motivating quantitative head selection and a brief calibration session. Although decoding gains depend on the dataset and backbone, our main findings concern that the sole use of architecture pressure promotes representation learning and alignment in a direction complementary to domain adaptation methods such as Euclidean Alignment. A per-subject low-rank adapter of only 2Cr parameters recover the full encoder's accuracy across five backbones and ranks r=1 to 16, so the per-subject module can be compressed by two to three orders of magnitude.
Sources
- Transfer Learning between Motor Imagery Datasets using Deep Learning -- Validation of Framework and Comparison of Datasets
- Evaluating the structure of cognitive tasks with transfer learning
- Scaling laws for decoding images from brain activity
- Physics-informed and Unsupervised Riemannian Domain Adaptation for Machine Learning on Heterogeneous EEG Datasets
- Decoding individual words from non-invasive brain recordings across 723 participants
- Brain-to-Text Decoding: A Non-invasive Approach via Typing
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: Local-Consistency Optimisation for Bayesian Neural Networks
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks