CDBG: Causally Motivated Dual-Invariance Learning against Topological and Predictive Shifts in EEG Workload Recognition
CDBG significantly outperforms state-of-the-art cross-subject and graph-based baselines, improving the Macro-F1 score by up to 4.23%, while simultaneously providing neurophysiologically interpretable functional rationales.
Yu-Zhe Zhang, Wen-Min Zhou, Cheng-Xi Xie et al.
· 0 citations