What Causes Performance Degradation in Cross-Subject EEG Classification?
arXiv:2410.03057
The paper systematically studies why cross‑subject EEG classification performs worse than subject‑dependent classification, identifying inter‑subject variability and shortcut learning as the main causes and showing how different EEG tasks are affected by each factor.
Abstract
Cross-subject Electroencephalography (EEG) classification typically achieves significantly lower performance than subject-dependent settings. Although this phenomenon has been widely observed in the literature, the underlying causes have not been systematically studied. In this paper, we design a series of controlled experiments to investigate the mechanisms behind the performance drop in cross-subject EEG classification across different EEG tasks. We show that the performance degradation can generally be attributed to two factors: inter-subject variability and shortcut learning. Specifically, multi-class-per-subject EEG classification tasks, such as motor imagery, emotion recognition, and ERP stimulus classification, are mainly affected by inter-subject variability, whereas single-class-per-subject EEG classification tasks, such as brain disease detection, are primarily influenced by shortcut learning based on subject-specific features. These findings provide new insights into the challenges of cross-subject EEG classification and emphasize the importance of appropriate evaluation protocols in EEG research. The code is available at https://github.com/DL4mHealth/EEG-Cross-Subject.
Accepted by the IEEE International Conference on Systems, Man, and Cybernetics (IEEE SMC 2026)