We formulate an unsupervised framework for multi-task sparse feature learning based on a novel dictionary learning algorithm. To solve the unsupervised learning problem, we propose a two-stage Multi-Source Multi-Target Dictionary Learning (MMDL) algorithm. In stage 1, we propose a multi-source dictionary learning method to utilize the common and individual sparse features in different time slots. In stage 2, supported by a rigorous theoretical analysis, we develop a multi-task learning method to solve the missing label problem.
Please refer to the file Readme_MMDL_1.0.txt to use the MMDL package.
This work has already been published at IPMI 2017 https://link.springer.com/chapter/10.1007/978-3-319-59050-9_15. If you find the MMDL package useful, please cite our work as follows:
Jie Zhang*, Qingyang Li* (co-first author), Richard J. Caselli, Jieping Ye, Yalin Wang. "Multi-Source Multi-Target Dictionary Learning for Prediction of Cognitive Decline", The 24th biennial international conference on Information Processing in Medical Imaging (IPMI), 2017.
Multi-Task Dictionary Learning
version 1.0
Authors: Qingyang Li liqingyanghappy@gmail.com Jie Zhang Jiezhang.Joena@asu.edu