ABSTRACT
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.
- Alexandre Abraham, Michael P Milham, Adriana Di Martino, R Cameron Craddock, Dimitris Samaras, Bertrand Thirion, and Gael Varoquaux. 2017. Deriving reproducible biomarkers from multi-site resting-state data: An Autism-based example. NeuroImage , Vol. 147 (2017), 736--745.Google ScholarCross Ref
- Nesreen K Ahmed, Nick Duffield, and Liangzhen Xia. 2018a. Sampling for approximate bipartite network projection. In Proceedings of the 27th International Joint Conference on Artificial Intelligence. AAAI Press, 3286--3292.Google ScholarCross Ref
- Nesreen K Ahmed, Jennifer Neville, Ryan A Rossi, and Nick Duffield. 2015. Efficient graphlet counting for large networks. In ICDM. IEEE, 1--10.Google Scholar
- Nesreen K Ahmed, Jennifer Neville, Ryan A Rossi, Nick G Duffield, and Theodore L Willke. 2017. Graphlet decomposition: Framework, algorithms, and applications. Knowledge and Information Systems , Vol. 50, 3 (2017), 689--722.Google ScholarDigital Library
- Nesreen K Ahmed, Ryan Rossi, John Boaz Lee, Xiangnan Kong, Theodore L Willke, Rong Zhou, and Hoda Eldardiry. 2018b. Learning Role-based Graph Embeddings. ICML workshop on StarAI (2018).Google Scholar
- Zilong Bai, Peter Walker, Anna Tschiffely, Fei Wang, and Ian Davidson. 2017. Unsupervised Network Discovery for Brain Imaging Data. In SIGKDD. ACM, 55--64.Google Scholar
- Danielle S Bassett and Edward T Bullmore. 2009. Human brain networks in health and disease. Current opinion in neurology , Vol. 22, 4 (2009), 340.Google Scholar
- Miguel Ángel Bautista, Artsiom Sanakoyeu, and Björn Ommer. 2017. Deep Unsupervised Similarity Learning using Partially Ordered Sets.. In CVPR . 1923--1932.Google Scholar
- Mikhail Belkin and Partha Niyogi. 2003. Laplacian eigenmaps for dimensionality reduction and data representation. Neural computation , Vol. 15, 6 (2003), 1373--1396.Google Scholar
- Austin R Benson, David F Gleich, and Jure Leskovec. 2016. Higher-order organization of complex networks. Science , Vol. 353, 6295 (2016), 163--166.Google Scholar
- Maxwell A Bertolero, BT Thomas Yeo, and Mark D'Esposito. 2015. The modular and integrative functional architecture of the human brain. Proceedings of the National Academy of Sciences , Vol. 112, 49 (2015), E6798--E6807.Google ScholarCross Ref
- Susan Y Bookheimer et al. 2018. The lifespan Human Connectome Project in aging: An overview. NeuroImage (2018).Google Scholar
- Jane Bromley, Isabelle Guyon, Yann LeCun, Eduard S"ackinger, and Roopak Shah. 1994. Signature verification using a" siamese" time delay neural network. In NeurIPS . 737--744.Google Scholar
- Joan Bruna, Wojciech Zaremba, Arthur Szlam, and Yann LeCun. 2013. Spectral networks and locally connected networks on graphs. arXiv preprint arXiv:1312.6203 (2013).Google Scholar
- James P Canning, Emma E Ingram, Sammantha Nowak-Wolff, Adriana M Ortiz, Nesreen K Ahmed, Ryan A Rossi, Karl RB Schmitt, and Sucheta Soundarajan. 2018. Predicting graph categories from structural properties. arXiv preprint arXiv:1805.02682 (2018).Google Scholar
- Bokai Cao, Liang Zhan, Xiangnan Kong, Philip S Yu, Nathalie Vizueta, Lori L Altshuler, and Alex D Leow. 2015. Identification of discriminative subgraph patterns in fMRI brain networks in bipolar affective disorder. In International Conference on Brain Informatics and Health. Springer, 105--114.Google ScholarCross Ref
- Gal Chechik, Uri Shalit, Varun Sharma, and Samy Bengio. 2009. An online algorithm for large scale image similarity learning. In NeurIPS . 306--314.Google Scholar
- Sumit Chopra, Raia Hadsell, and Yann LeCun. 2005. Learning a similarity metric discriminatively, with application to face verification. In CVPR , Vol. 1. IEEE, 539--546.Google ScholarDigital Library
- Michaël Defferrard, Xavier Bresson, and Pierre Vandergheynst. 2016. Convolutional neural networks on graphs with fast localized spectral filtering. In NeurIPS . 3844--3852.Google Scholar
- Adriana Di Martino, Chao-Gan Yan, Qingyang Li, Erin Denio, Francisco X Castellanos, Kaat Alaerts, Jeffrey S Anderson, Michal Assaf, Susan Y Bookheimer, Mirella Dapretto, et almbox. 2014. The autism brain imaging data exchange: towards a large-scale evaluation of the intrinsic brain architecture in autism. Molecular psychiatry , Vol. 19, 6 (2014), 659.Google Scholar
- Brendan J Frey and Delbert Dueck. 2007. Clustering by passing messages between data points. science , Vol. 315, 5814 (2007), 972--976.Google Scholar
- Michael Greicius. 2008. Resting-state functional connectivity in neuropsychiatric disorders. Current opinion in neurology , Vol. 21, 4 (2008), 424--430.Google Scholar
- Guo-Dong Guo, Anil K Jain, Wei-Ying Ma, and Hong-Jiang Zhang. 2001. Learning similarity measure for natural image retrieval with relevance feedback. In CVPR , Vol. 1. IEEE, I--I.Google Scholar
- Patric Hagmann, Leila Cammoun, Xavier Gigandet, Reto Meuli, Christopher J Honey, Van J Wedeen, and Olaf Sporns. 2008. Mapping the structural core of human cerebral cortex. PLoS biology , Vol. 6, 7 (2008), e159.Google Scholar
- Klaus Hechenbichler and Klaus Schliep. 2004. Weighted k-nearest-neighbor techniques and ordinal classification. (2004).Google Scholar
- CJ Honey, O Sporns, Leila Cammoun, Xavier Gigandet, Jean-Philippe Thiran, Reto Meuli, and Patric Hagmann. 2009. Predicting human resting-state functional connectivity from structural connectivity. Proceedings of the National Academy of Sciences , Vol. 106, 6 (2009), 2035--2040.Google ScholarCross Ref
- Diederik P Kingma and Jimmy Ba. 2014. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014).Google Scholar
- Gregory Koch, Richard Zemel, and Ruslan Salakhutdinov. 2015. Siamese neural networks for one-shot image recognition. In ICML Deep Learning Workshop , Vol. 2.Google Scholar
- Sofia Ira Ktena, Sarah Parisot, Enzo Ferrante, Martin Rajchl, Matthew Lee, Ben Glocker, and Daniel Rueckert. 2018. Metric learning with spectral graph convolutions on brain connectivity networks. NeuroImage , Vol. 169 (2018), 431--442.Google ScholarCross Ref
- Qimai Li, Zhichao Han, and Xiao-Ming Wu. 2018. Deeper Insights into Graph Convolutional Networks for Semi-Supervised Learning. arXiv preprint arXiv:1801.07606 (2018).Google Scholar
- Jin Liu, Min Li, Yi Pan, Wei Lan, Ruiqing Zheng, Fang-Xiang Wu, and Jianxin Wang. 2017. Complex brain network analysis and its applications to brain disorders: a survey. Complexity , Vol. 2017 (2017).Google Scholar
- Lorenzo Livi and Antonello Rizzi. 2013. The graph matching problem. Pattern Analysis and Applications , Vol. 16, 3 (2013), 253--283.Google ScholarDigital Library
- Guixiang Ma, Lifang He, Bokai Cao, Jiawei Zhang, S Yu Philip, and Ann B Ragin. 2016. Multi-graph clustering based on interior-node topology with applications to brain networks. In ECML PKDD. Springer, 476--492.Google Scholar
- Guixiang Ma, Lifang He, Chun-Ta Lu, Weixiang Shao, Philip S Yu, Alex D Leow, and Ann B Ragin. 2017a. Multi-view clustering with graph embedding for connectome analysis. In CIKM. ACM, 127--136.Google Scholar
- Guixiang Ma, Chun-Ta Lu, Lifang He, S Yu Philip, and Ann B Ragin. 2017b. Multi-view graph embedding with hub detection for brain network analysis. In ICDM. IEEE, 967--972.Google Scholar
- Bryan Perozzi, Rami Al-Rfou, and Steven Skiena. 2014. Deepwalk: Online learning of social representations. In SIGKDD. ACM, 701--710.Google ScholarDigital Library
- Jonathan D Power, Alexander L Cohen, Steven M Nelson, Gagan S Wig, Kelly Anne Barnes, Jessica A Church, Alecia C Vogel, Timothy O Laumann, Fran M Miezin, Bradley L Schlaggar, et almbox. 2011. Functional network organization of the human brain. Neuron , Vol. 72, 4 (2011), 665--678.Google ScholarCross Ref
- Ann B. Ragin, Hongyan Du, Renee Ochs, Ying Wu, Christina L Sammet, Alfred Shoukry, and Leon G Epstein. 2012. Structural brain alterations can be detected early in HIV infection. Neurology , Vol. 79, 24 (2012), 2328--2334.Google ScholarCross Ref
- Ryan A Rossi, Nesreen K Ahmed, Aldo Carranza, David Arbour, Anup Rao, Sungchul Kim, and Eunyee Koh. 2019. Heterogeneous network motifs. arXiv preprint arXiv:1901.10026 (2019).Google Scholar
- Ryan A Rossi, Nesreen K Ahmed, Hoda Eldardiry, and Rong Zhou. 2018b. Similarity-based Multi-label Learning. In 2018 International Joint Conference on Neural Networks (IJCNN). IEEE, 1--8.Google Scholar
- Ryan A Rossi, Nesreen K Ahmed, and Eunyee Koh. 2018a. Higher-order Network Representation Learning. In WWW. International World Wide Web Conferences Steering Committee, 3--4.Google Scholar
- Ryan A Rossi, Rong Zhou, and Nesreen K Ahmed. 2017. Deep feature learning for graphs. arXiv preprint arXiv:1704.08829 (2017).Google Scholar
- Ryan A Rossi, Rong Zhou, Nesreen K Ahmed, and Hoda Eldardiry. 2018c. Relational Similarity Machines (RSM): A Similarity-based Learning Framework for Graphs. In 2018 IEEE International Conference on Big Data (Big Data). IEEE, 1807--1816.Google ScholarCross Ref
- David I Shuman, Sunil K Narang, Pascal Frossard, Antonio Ortega, and Pierre Vandergheynst. 2013. The emerging field of signal processing on graphs: Extending high-dimensional data analysis to networks and other irregular domains. IEEE Signal Processing Magazine , Vol. 30, 3 (2013), 83--98.Google ScholarCross Ref
- Lindsay I Smith. 2002. A tutorial on principal components analysis . Technical Report.Google Scholar
- Marjolein Spronk, Jie Lisa Ji, Kaustubh Kulkarni, Grega Repovs, Alan Anticevic, and Michael W Cole. 2018. Mapping the human brain's cortical-subcortical functional network organization. bioRxiv (2018), 206292.Google Scholar
- Sylvain Takerkart, Guillaume Auzias, Bertrand Thirion, and Liva Ralaivola. 2014. Graph-based inter-subject pattern analysis of fMRI data. PloS one , Vol. 9, 8 (2014), e104586.Google ScholarCross Ref
- Shin Teng, Chia-Feng Lu, Po-Shan Wang, Cheng-Ta Li, Pei-Chi Tu, Chih-I Hung, Tung-Ping Su, and Yu-Te Wu. 2014. Altered resting-state functional connectivity of striatal-thalamic circuit in bipolar disorder. PloS one , Vol. 9, 5 (2014), e96422.Google ScholarCross Ref
- David C Van Essen, Stephen M Smith, Deanna M Barch, Timothy EJ Behrens, Essa Yacoub, Kamil Ugurbil, Wu-Minn HCP Consortium, et almbox. 2013. The WU-Minn human connectome project: an overview. Neuroimage , Vol. 80 (2013), 62--79.Google ScholarCross Ref
- Jiang Wang, Yang Song, Thomas Leung, Chuck Rosenberg, Jingbin Wang, James Philbin, Bo Chen, and Ying Wu. 2014. Learning fine-grained image similarity with deep ranking. In CVPR. 1386--1393.Google Scholar
- Shen Wang, Lifang He, Bokai Cao, Chun-Ta Lu, Philip S Yu, and Ann B Ragin. 2017. Structural deep brain network mining. In SIGKDD. ACM, 475--484.Google Scholar
- Susan Whitfield-Gabrieli and Alfonso Nieto-Castanon. 2012. Conn: a functional connectivity toolbox for correlated and anticorrelated brain networks. Brain connectivity , Vol. 2, 3 (2012), 125--141.Google Scholar
- Mingrui Xia, Jinhui Wang, and Yong He. 2013. BrainNet Viewer: a network visualization tool for human brain connectomics. PloS one , Vol. 8, 7 (2013), e68910.Google ScholarCross Ref
Index Terms
- Deep Graph Similarity Learning for Brain Data Analysis
Recommendations
Brain network analysis: a data mining perspective
Following the recent advances in neuroimaging technology, the research on brain network analysis becomes an emerging area in data mining community. Brain network data pose many unique challenges for data mining research. For example, in brain networks, ...
Deep Representation Learning for Multimodal Brain Networks
Medical Image Computing and Computer Assisted Intervention – MICCAI 2020AbstractApplying network science approaches to investigate the functions and anatomy of the human brain is prevalent in modern medical imaging analysis. Due to the complex network topology, for an individual brain, mining a discriminative network ...
Intrinsic Brain Connectivity Associated with Pragmatic Language Impairment in Children with Autism
ICBBT '23: Proceedings of the 2023 15th International Conference on Bioinformatics and Biomedical TechnologyImpairment in pragmatic language is one of the most noticeable symptoms of autism spectrum disorders (ASD). Abnormal activity in the inferior frontal gyrus (IFG), a critical language area associated with pragmatic meaning processing, has been repeatedly ...
Comments