AlphaGrad: Normalized Gradient Descent for Adaptive Multi-loss Functions in EEG-based Motor Imagery Classification

• Published in: IEEE journal of biomedical and health informatics Vol. PP; pp. 1 - 13
• Main Authors: Chaisaen, Rattanaphon, Autthasan, Phairot, Ditthapron, Apiwat, Wilaiprasitporn, Theerawit
• Format: Journal Article
• Language: English
• Published: United States IEEE 22.05.2025
• Subjects: Adaptation models; adaptive loss blending; Brain modeling; Brain-computer interfaces; Classification algorithms; Electroencephalography; Feature extraction; Filter banks; Measurement; motor imagery EEG; Motors; multi-task learning; Multitasking; normalized gradient descent; Training
• ISSN: 2168-2194; 2168-2208; 2168-2208
• DOI: 10.1109/JBHI.2025.3572197

In this study, we propose AlphaGrad, a novel adaptive loss blending strategy for optimizing multi-task learning (MTL) models in motor imagery (MI)-based electroencephalography (EEG) classification. AlphaGrad is the first method to automatically adjust multi-loss functions with differing metric scales, including mean square error, cross-entropy, and deep metric learning, within the context of MI-EEG. We evaluate AlphaGrad using two state-of-the-art MTL-based neural networks, MIN2Net and FBMSNet, across four benchmark datasets. Experimental results show that AlphaGrad consistently outperforms existing strategies such as AdaMT, GradApprox, and fixed-weight baselines in classification accuracy and training stability. Compared to baseline static weighting, AlphaGrad achieves over 10% accuracy improvement on subject-independent MI tasks when evaluated on the largest benchmark dataset. Furthermore, AlphaGrad demonstrates robust adaptability across various EEG paradigms-including steady-state visually evoked potential (SSVEP) and event-related potential (ERP), making it broadly applicable to brain-computer interface (BCI) systems. We also provide gradient trajectory visualizations highlighting AlphaGrad's ability to maintain training stability and avoid local minima. These findings underscore AlphaGrad's promise as a general-purpose solution for adaptive multi-loss optimization in biomedical time-series learning.