Publications -> Conference Papers

ROM: A Robust Online Multi-Task Learning Approach


Authors: C. Zhang, P. Zhao, S. Hao, Y. C. Soh, and B. S. Lee
Title: ROM: A Robust Online Multi-Task Learning Approach
Abstract: A series of online multi-task learning (OMTL) algorithms have been proposed to avoid the expensive training cost and poor adaptability of traditional batch multi-task learning (MTL) algorithms in recent years. However, these OMTL algorithms usually assume that all tasks are closely related, which may not hold in practical scenarios. More importantly, their theoretical reliability is weakened due to the lack of proof on the cumulative regrets. To overcome these limitations, we present a robust online multi-task classification framework (ROM) and its two optimization algorithms (ROM-PGD, ROM-RDA). The proposed algorithms can not only automatically capture the common features among all tasks and individual features for each task, but also identify the potential existence of outlier task. Theoretically, we prove that the regret bounds of these two algorithms are sub-linear compared with the best separating algorithm in hindsight. Empirical studies on both synthetic and real-world datasets also demonstrate the effectiveness of our proposed algorithms when compared with the state-of-the-art OMTL algorithms.
Keywords: 
Conference Name: IEEE 16th International Conference on Data Mining (ICDM'16)
Location: Barcelona, Spain
Publisher: IEEE
Year: 2016
Accepted PDF File: ROM_A_Robust_Online_Multi-Task_Learning_Approach_accepted.pdf
Permanent Link: https://doi.org/10.1109/ICDM.2016.0183
Reference: C. Zhang, P. Zhao, S. Hao, Y. C. Soh, and B. S. Lee, “ROM: A robust online multi-task learning approach,” in Proceedings of the IEEE 16th International Conference on Data Mining (ICDM’16). IEEE, December 2016, pp. 1341–1346.
bibtex: 
@inproceedings{LILY-c107, 
   author = {Zhang, Chi and Zhao, Peilin and Hao, Shuji and Soh, Yeng Chai and Lee, Bu Sung},
   title  = {{ROM}: A Robust Online Multi-Task Learning Approach},  
   booktitle = {Proceedings of the IEEE 16th International Conference on Data Mining (ICDM'16)}, 
   year  = {2016}, 
   month = {December}, 
   pages = {1341-1346}, 
   location = {Barcelona, Spain},
   publisher = {IEEE},
}