Abstract
Multi-task learning has been widely applied to Alzheimer’s Disease (AD) studies due to its capability of simultaneously rating the disease severity (classification) and predicting corresponding clinical scores (regression). In this article, we propose a novel technique of Adaptive Multi-task Dual-Structured Learning, named AMDSL, by mutually exploring the dual manifold structure for the label and regression score of the disease data under joint classification and regression tasks, while learning an adaptive shared similarity measure and corresponding feature mapping among these two tasks. We encode both the reconstructed label representation and regression score adaptive to the ideal similarity measure on disease data to achieve the ideal performance on these two joint tasks. The alternating algorithm is proposed to optimize the above objective. We theoretically prove the convergence of the optimization algorithm. The superiority of AMDSL is experimentally validated under joint classification and regression as per various evaluation metrics against the most authoritative Alzheimer’s disease data.
- Alzheimer’s Association. 2018. 2018 Alzheimer’s disease facts and figures. Alzheimer’s & Dementia 14 (2018), 367–429.Google Scholar
- Lodewijk Brand, Hua Wang, Heng Huang, Shannon L. Risacher, Andrew J. Saykin, and Li Shen. [n.d.]. Joint high-order multi-task feature learning to predict the progression of Alzheimer’s disease. In Medical Image Computing and Computer Assisted Intervention, 21st International Conference, Proceedings, Part I (MICCAI ’18) (Lecture Notes in Computer Science), Vol. 11070. 555–562.Google Scholar
- Peng Cao, Xuanfeng Shan, Dazhe Zhao, Min Huang, and Osmar R. Zaïane. 2017. Sparse shared structure based multi-task learning for MRI based cognitive performance prediction of Alzheimer’s disease. Pattern Recognit. 72 (2017), 219–235. Google Scholar
Digital Library
- Young-Sang Cho, Joon-Kyung Seong, Yong Jeong, and Sung Yong Shin. 2012. Individual subject classification for Alzheimer’s disease based on incremental learning using a spatial frequency representation of cortical thickness data. NeuroImage 59, 3 (2012), 2217–2230.Google Scholar
Cross Ref
- Xin Geng. 2016. Label distribution learning. IEEE Trans. Knowl. Data Eng. 28, 7 (2016), 1734–1748.Google Scholar
Cross Ref
- Peng Hou, Xin Geng, and Min-Ling Zhang. 2016. Multi-label manifold learning. In Proceedings of the 30th AAAI Conference on Artificial Intelligence. AAAI Press, 1680–1686. Google Scholar
Digital Library
- Pengbo Jiang, Xuetong Wang, Qiongling Li, Leiming Jin, and Shuyu Li. 2019. Correlation-aware sparse and low-rank constrained multi-task learning for longitudinal analysis of Alzheimer’s disease. IEEE J. Biomed. Health Informatics 23, 4 (2019), 1450–1456.Google Scholar
Cross Ref
- Biao Jie, Mingxia Liu, Jun Liu, Daoqiang Zhang, and Dinggang Shen. 2017. Temporally constrained group sparse learning for longitudinal data analysis in Alzheimer’s disease. IEEE Trans. Biomed. Eng. 64, 1 (2017), 238–249.Google Scholar
Cross Ref
- Feng Liu, Chong-Yaw Wee, Huafu Chen, and Dinggang Shen. 2014. Inter-modality relationship constrained multi-modality multi-task feature selection for Alzheimer’s Disease and mild cognitive impairment identification. NeuroImage 84 (2014), 466–475.Google Scholar
Cross Ref
- Mingxia Liu, Jun Zhang, Ehsan Adeli, and Dinggang Shen. 2017. Deep multi-task multi-channel learning for joint classification and regression of brain status. In Medical Image Computing and Computer Assisted Intervention, 20th International Conference, Proceedings, Part III (MICCAI ’ 17) (Lecture Notes in Computer Science), Vol. 10435. Springer, 3–11.Google Scholar
- Mingxia Liu, Jun Zhang, Ehsan Adeli, and Dinggang Shen. 2019. Joint classification and regression via deep multi-task multi-channel learning for Alzheimer’s disease diagnosis. IEEE Trans. Biomed. Eng. 66, 5 (2019), 1195–1206.Google Scholar
Cross Ref
- Feiping Nie, Heng Huang, Xiao Cai, and Chris H. Q. Ding. 2010. Efficient and robust feature selection via joint \(\)-norms minimization. In Advances in Neural Information Processing Systems 23: 24th Annual Conference on Neural Information Processing Systems 2010, Proceedings. Curran Associates, Inc., 1813–1821. Google Scholar
Digital Library
- Liqiang Nie, Luming Zhang, Lei Meng, Xuemeng Song, Xiaojun Chang, and Xuelong Li. 2017. Modeling disease progression via multisource multitask learners: A case study with Alzheimer’s disease. IEEE Trans. Neural Networks Learn. Syst. 28, 7 (2017), 1508–1519.Google Scholar
Cross Ref
- Tianji Pang, Feiping Nie, Junwei Han, and Xuelong Li. 2019. Efficient feature selection via \(\)norm constrained sparse regression. IEEE Trans. Knowl. Data Eng. 31, 5 (2019), 880–893.Google Scholar
Cross Ref
- Hanyang Peng and Yong Fan. 2017. A general framework for sparsity regularized feature selection via iteratively reweighted least square minimization. In Proceedings of the 31st AAAI Conference on Artificial Intelligence (AAAI ’17). AAAI Press, 2471–2477. Google Scholar
Digital Library
- Hanyang Peng and Yong Fan. 2017. A general framework for sparsity regularized feature selection via iteratively reweighted least square minimization. In Proceedings of the 31st AAAI Conference on Artificial Intelligence, AAAI Press, 2471–2477. Google Scholar
Digital Library
- Mert R. Sabuncu and Ender Konukoglu. 2015. Clinical prediction from structural brain MRI scans: A large-scale empirical study. Neuroinformatics 13, 1 (2015), 31–46.Google Scholar
Cross Ref
- Matt Silver, Eva Janousová, Xue Hua, Paul M. Thompson, and Giovanni Montana. 2012. Identification of gene pathways implicated in Alzheimer’s disease using longitudinal imaging phenotypes with sparse regression. NeuroImage 63, 3 (2012), 1681–1694.Google Scholar
Cross Ref
- Rodrigo G. F. Soares, Huanhuan Chen, and Xin Yao. 2017. A cluster-based semisupervised ensemble for multiclass classification. IEEE Trans. Emerging Topics Comput. Intellig. 1, 6 (2017), 408–420.Google Scholar
Cross Ref
- Cynthia M. Stonnington, Carlton Chu, Stefan Klöppel, Clifford R. Jack Jr., John Ashburner, and Richard S. Frackowiak. 2010. Predicting clinical scores from magnetic resonance scans in Alzheimer’s disease. NeuroImage 51, 4 (2010), 1405–1413.Google Scholar
Cross Ref
- Maria Vounou, Eva Janousová, Robin Wolz, Jason L. Stein, Paul M. Thompson, Daniel Rueckert, and Giovanni Montana. 2012. Sparse reduced-rank regression detects genetic associations with voxel-wise longitudinal phenotypes in Alzheimer’s disease. NeuroImage 60, 1 (2012), 700–716.Google Scholar
Cross Ref
- Jing Wan, Zhilin Zhang, Jingwen Yan, Taiyong Li, Bhaskar D. Rao, Shiaofen Fang, Sungeun Kim, Shannon L. Risacher, Andrew J. Saykin, and Li Shen. 2012. Sparse Bayesian multi-task learning for predicting cognitive outcomes from neuroimaging measures in Alzheimer’s disease. In 2012 IEEE Conference on Computer Vision and Pattern Recognition. IEEE Computer Society, 940–947. Google Scholar
Digital Library
- Hua Wang, Feiping Nie, Heng Huang, Shannon L. Risacher, Chris H. Q. Ding, Andrew J. Saykin, and Li Shen. 2011. Sparse multi-task regression and feature selection to identify brain imaging predictors for memory performance. In IEEE International Conference on Computer Vision (ICCV’11), Dimitris N. Metaxas, Long Quan, Alberto Sanfeliu, and Luc Van Gool (Eds.). IEEE Computer Society, 557–562. Google Scholar
Digital Library
- Liping Wang and Songcan Chen. 2013. \(\) matrix norm and its application in feature selection. CoRR abs/1303.3987 (2013).Google Scholar
- Mingliang Wang, Daoqiang Zhang, Dinggang Shen, and Mingxia Liu. 2019. Multi-task exclusive relationship learning for Alzheimer’s disease progression prediction with longitudinal data. Med. Image Anal. 53 (2019), 111–122.Google Scholar
Cross Ref
- Yang Wang, Xiaodi Huang, and Lin Wu. 2013. Clustering via geometric median shift over Riemannian manifolds. Inf. Sci. 220 (2013), 292–305. DOI:https://doi.org/10.1016/j.ins.2012.07.009 Online Fuzzy Machine Learning and Data Mining. Google Scholar
Digital Library
- Yang Wang, Xuemin Lin, Lin Wu, Wenjie Zhang, Qing Zhang, and Xiaodi Huang. 2015. Robust subspace clustering for multi-view data by exploiting correlation consensus. IEEE Trans. Image Process. 24, 11 (2015), 3939–3949.Google Scholar
Digital Library
- Yang Wang, Lin Wu, Xuemin Lin, and Junbin Gao. 2018. Multiview spectral clustering via structured low-rank matrix factorization. IEEE Trans. Neural Networks Learning Syst. 29, 10 (2018), 4833–4843.Google Scholar
Cross Ref
- Yang Wang, Wenjie Zhang, Lin Wu, Xuemin Lin, Meng Fang, and Shirui Pan. 2016. Iterative views agreement: An iterative low-rank based structured optimization method to multi-view spectral clustering. In Proceedings of the 25th International Joint Conference on Artificial Intelligence (IJCAI’16). AAAI Press, 2153–2159. Google Scholar
Digital Library
- Lin Wu, Yang Wang, and Ling Shao. 2019. Cycle-consistent deep generative hashing for cross-modal retrieval. IEEE Trans. Image Process. 28, 4 (2019), 1602–1612.Google Scholar
Digital Library
- Kun Zhan, Chaoxi Niu, Changlu Chen, Feiping Nie, Changqing Zhang, and Yi Yang. 2019. Graph structure fusion for multiview clustering. IEEE Trans. Knowl. Data Eng. 31, 10 (2019), 1984–1993.Google Scholar
Cross Ref
- Daoqiang Zhang and Dinggang Shen. 2012. Multi-modal multi-task learning for joint prediction of multiple regression and classification variables in Alzheimer’s disease. NeuroImage 59, 2 (2012), 895–907.Google Scholar
Cross Ref
- Xiantong Zhen, Mengyang Yu, Xiaofei He, and Shuo Li. 2018. Multi-target regression via robust low-rank learning. IEEE Trans. Pattern Anal. Mach. Intell. 40, 2 (2018), 497–504. Google Scholar
Digital Library
- Xiaofeng Zhu, Xuelong Li, and Shichao Zhang. 2016. Block-row sparse multiview multilabel learning for image classification. IEEE Trans. Cybernetics 46, 2 (2016), 450–461.Google Scholar
Cross Ref
- Xiaofeng Zhu, Heung-Il Suk, and Dinggang Shen. 2014. A novel matrix-similarity based loss function for joint regression and classification in AD diagnosis. NeuroImage 100 (2014), 91–105.Google Scholar
Cross Ref
- Xiaofeng Zhu, Heung-Il Suk, Li Wang, Seong-Whan Lee, and Dinggang Shen. 2017. A novel relational regularization feature selection method for joint regression and classification in AD diagnosis. Med. Image Anal. 38 (2017), 205–214.Google Scholar
Cross Ref
- Xiaofeng Zhu, Shichao Zhang, Rongyao Hu, Yonghua Zhu, and Jingkuan Song. 2018. Local and global structure preservation for robust unsupervised spectral feature selection. IEEE Trans. Knowl. Data Eng. 30, 3 (2018), 517–529.Google Scholar
Cross Ref
- Yue Zhu, James T. Kwok, and Zhi-Hua Zhou. 2018. Multi-label learning with global and local label correlation. IEEE Trans. Knowl. Data Eng. 30, 6 (2018), 1081–1094.Google Scholar
Index Terms
Adaptive Multi-Task Dual-Structured Learning with Its Application on Alzheimer’s Disease Study
Recommendations
A multi-task learning formulation for predicting disease progression
KDD '11: Proceedings of the 17th ACM SIGKDD international conference on Knowledge discovery and data miningAlzheimer's Disease (AD), the most common type of dementia, is a severe neurodegenerative disorder. Identifying markers that can track the progress of the disease has recently received increasing attentions in AD research. A definitive diagnosis of AD ...
Dual feature correlation guided multi-task learning for Alzheimer's disease prediction
AbstractAlzheimer's disease (AD) is a gradually progressive neurodegenerative disease affecting cognition functions. Predicting the cognitive scores from neuroimage measures and identifying relevant imaging biomarkers are important research ...
Highlights- We incorporate the feature correlation structure to facilitate multi-task learning.
Exploiting task relationships for Alzheimer’s disease cognitive score prediction via multi-task learning
AbstractAlzheimer’s disease (AD) is highly prevalent and a significant cause of dementia and death in elderly individuals. Motivated by breakthroughs of multi-task learning (MTL), efforts have been made to extend MTL to improve the Alzheimer’s ...
Highlights- Two graph-guided regularization terms are proposed.
- A self-paced multi-task ...






Comments