Adaptive Domain Alignment Neural Networks for Cross-Domain EEG Emotion Recognition

作     者：Hong, Xuezhu Du, Changde He, Huiguang 

作者机构：Chinese Academy of Sciences Key Laboratory of Brain Cognition and Brain-inspired Intelligence Technology Institute of Automation Beijing100190 China University of Chinese Academy of Sciences School of Artificial Intelligence Beijing100049 China 

出 版 物：《IEEE Transactions on Affective Computing》 (IEEE Trans. Affective Comput.)

年 卷 期：2025年第16卷第2期

页      面：903-914页

核心收录：

学科分类：0808[工学-电气工程] 08[工学] 070206[理学-声学] 0835[工学-软件工程] 0714[理学-统计学（可授理学、经济学学位）] 0701[理学-数学] 0812[工学-计算机科学与技术（可授工学、理学学位）] 0702[理学-物理学] 

基　　金：This work was supported in part by the Beijing Natural Science Foundation under Grant J210010  in part by the National Natural Science Foundation of China under Grant 62206284  and in part by the Beijing Nova Program 

主　　题：Emotion Recognition 

摘      要：Electroencephalography (EEG) - based Emotion recognition is now facing great challenge of the intra- and inter-subject variability of EEG signal. Researchers attempted to handle this challenge by using transfer learning methods which usually share two main limitations: most of these methods align marginal distributions instead of conditional distributions of source and target data, making the alignment process classwise ambiguous;also, they prefer to use Multi-Layer Perceptron (MLP) with redundant parameters as classifiers, which is shown by recent research that could result serious over-fitting towards labeled data and prevent the model to draw a proper representation space. In our work, we propose a novel domain alignment method: Adaptive Domain Alignment Neural Networks (ADANN). Our method directly model conditional distributions of source and target domains by two sets of label-wise prototypes, representing the density maximum of each class, while the normalized correspond similarity naturally represents the conditional probability. The predicted label for a sample is given by the argument maxima of similarities and therefore the MLP classifier is not required. Using context-instance contrastive learning to align two sets of prototypes, their corresponding conditional distributions are being learned simultaneously. Exhaustive cross-domain experiments have been conducted under protocols that are strongly related to practical application scenarios and our proposed method achieves better or similar performance compared with recent state-of-the-art methods. © 2010-2012 IEEE.