Deep Graph Similarity Learning for Brain Data Analysis
Proceedings of the 28th ACM International Conference on Information and Knowledge Management(2019)
摘要
We propose an end-to-end graph similarity learning framework called Higher-order Siamese GCN for multi-subject fMRI data analysis. The proposed framework learns the brain network representations via a supervised metric-based approach with siamese neural networks using two graph convolutional networks as the twin networks. Our proposed framework performs higher-order convolutions by incorporating higher-order proximity in graph convolutional networks to characterize and learn the community structure in brain connectivity networks. To the best of our knowledge, this is the first community-preserving graph similarity learning framework for multi-subject brain network analysis. Experimental results on four real fMRI datasets demonstrate the potential use cases of the proposed framework for multi-subject brain analysis in health and neuropsychiatric disorders. Our proposed approach achieves an average AUC gain of $75$% compared to PCA, an average AUC gain of $65.5$% compared to Spectral Embedding, and an average AUC gain of $24.3$% compared to S-GCN across the four datasets, indicating promising applications in clinical investigation and brain disease diagnosis.
更多查看译文
关键词
brain networks, community embedding, community-preserving embedding, functional connectivity, graph convolutional networks, graph matching, graph neural networks, graph similarity, higher-order networks, metric learning, structural similarity
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络