Structure-Preserving Graph Kernel for Brain Network Classification
This work addresses brain network analysis for medical diagnosis and emotion recognition, offering a clinically interpretable method, but it is incremental as it builds on existing graph kernel approaches.
The paper tackled brain network classification by introducing a structure-preserving graph kernel that leverages natural graph structure for prior knowledge encoding, achieving superior performance on HIV disease classification and emotion recognition tasks compared to state-of-the-art methods, with results indicating that EEG-connectome information is primarily encoded in the alpha band during emotion regulation.
This paper presents a novel graph-based kernel learning approach for connectome analysis. Specifically, we demonstrate how to leverage the naturally available structure within the graph representation to encode prior knowledge in the kernel. We first proposed a matrix factorization to directly extract structural features from natural symmetric graph representations of connectome data. We then used them to derive a structure-persevering graph kernel to be fed into the support vector machine. The proposed approach has the advantage of being clinically interpretable. Quantitative evaluations on challenging HIV disease classification (DTI- and fMRI-derived connectome data) and emotion recognition (EEG-derived connectome data) tasks demonstrate the superior performance of our proposed methods against the state-of-the-art. Results showed that relevant EEG-connectome information is primarily encoded in the alpha band during the emotion regulation task.