CRCC: Contrast-Based Robust Cross-Subject and Cross-Site Representation Learning for EEG
This addresses generalization issues in clinical EEG analysis for applications like Major Depressive Disorder diagnosis, but is incremental as it builds on existing contrastive and adversarial methods.
The paper tackled the problem of EEG-based neural decoding models failing to generalize across acquisition sites due to site-dependent biases, and achieved a 10.7 percentage-point improvement in balanced accuracy under zero-shot site transfer.
EEG-based neural decoding models often fail to generalize across acquisition sites due to structured, site-dependent biases implicitly exploited during training. We reformulate cross-site clinical EEG learning as a bias-factorized generalization problem, in which domain shifts arise from multiple interacting sources. We identify three fundamental bias factors and propose a general training framework that mitigates their influence through data standardization and representation-level constraints. We construct a standardized multi-site EEG benchmark for Major Depressive Disorder and introduce CRCC, a two-stage training paradigm combining encoder-decoder pretraining with joint fine-tuning via cross-subject/site contrastive learning and site-adversarial optimization. CRCC consistently outperforms state-of-the-art baselines and achieves a 10.7 percentage-point improvement in balanced accuracy under strict zero-shot site transfer, demonstrating robust generalization to unseen environments.