Instance-Adaptive Graph for EEG Emotion Recognition

To tackle the individual differences and characterize the dynamic relationships among different EEG regions for EEG emotion recognition, in this paper, we propose a novel instance-adaptive graph method (IAG), which employs a more flexible way to construct graphic connections so as to present different graphic representations determined by different input instances. To fit the different EEG pattern, we employ an additional branch to characterize the intrinsic dynamic relationships between different EEG channels. To give a more precise graphic representation, we design the multilevel and multi-graph convolutional operation and the graph coarsening. Furthermore, we present a type of sparse graphic representation to extract more discriminative features. Experiments on two widely-used EEG emotion recognition datasets are conducted to evaluate the proposed model and the experimental results show that our method achieves the state-ofthe-art performance.

Authors

• Tengfei Song
• Suyuan Liu National University of Defense Technology
• Wenming Zheng Key Laboratory of Child Development and Learning Science of Ministry of Education
• Yuan Zong Key Laboratory of Child Development and Learning Science of Ministry of Education
• Zhen Cui School of Artificial Intelligence, Beijing Normal University

Keywords

No keywords are indexed for this paper.