CDBG: Causally Motivated Dual-Invariance Learning against Topological and Predictive Shifts in EEG Workload Recognition

2026-09-25

AI Summary

This study addresses the dual distribution shift in functional connectivity topology and predictive mechanisms caused by inter-subject variability in EEG-based mental workload recognition. To tackle this challenge, we propose a causality-driven double-invariant learning framework. By integrating a stochastic edge-masked graph neural network, the method achieves topological invariance through workload-conditional Laplacian spectral alignment, while ensuring predictive risk stability via Invariant Risk Minimization (IRM). This approach effectively decouples and mitigates cross-subject distribution shifts. Experimental results demonstrate that the proposed framework significantly outperforms state-of-the-art methods across multiple datasets, yielding a 4.23% improvement in Macro-F1 score. Furthermore, it delivers both high classification accuracy and neurophysiological interpretability.

Abstract

Generalizing Electroencephalography (EEG)-based mental workload recognition to unseen subjects remains a formidable challenge due to severe inter-subject variability. While functional brain graphs effectively model distributed cognitive dynamics, their inherent subject-specificity induces two coupled distribution shifts: a class-conditional topological shift in the underlying functional connectivity, and a predictive mechanism shift in the learned representation-to-label mapping. Motivated by the subject-induced distribution shifts, we propose CDBG, a Causally motivated Dual-invariance learning framework for Brain Graphs. CDBG disentangles and mitigates these shifts via a two-stage rationale learning pipeline. First, it employs stochastic edge masking to extract sparse, workload-predictive graph rationales, regularized by workload-conditional Laplacian spectral alignment to enforce topological invariance across subjects. Second, it applies subject-wise Invariant Risk Minimization (IRM) to the graph representations, ensuring environment-wise risk stationarity. Extensive experiments on a self-built air traffic controller EEG cognitive workload dataset and multiple public datasets under a strict leave-one-subject-out protocol demonstrate that 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.

Problem

• EEG workload recognition
• cross-subject generalization
• distribution shift
• functional brain graphs
• inter-subject variability

Innovation

• Brain Graphs
• Causal Invariance Learning
• Laplacian Spectral Alignment
• Invariant Risk Minimization
• EEG Workload Recognition