Individual and Global Models to Achieve an Overall Improvement for Multi-taskLearning

A.ArulMurugan*, **, A.Aishwarya***, R.Meena****, M.Gayathri*****
* Associate Professor, Department of Information Technology, A.V.C College of Engineering, Mannampandal, Mayiladuthurai, Tamilnadu. India.
**_***_****_***** Final year B.Tech (IT), Department of Information Technology, A.V.C College of Engineering, Mannampandal, Mayiladuthurai, Tamilnadu, India.
Periodicity:December - February'2015
DOI : https://doi.org/10.26634/jit.4.1.3280

Abstract

We study the matter of on-line multi-task learning for finding multiple connected classification tasks in parallel, aiming at classifying each sequence of knowledge received by every task accurately and expeditiously. One sensible example of on-line multi-task learning is the micro-blog sentiment detection on a gaggle of users that classifies micro-blog posts generated by every user into emotional or non-emotional classes. Initial of all, to satisfy the vital requirements of on-line applications, an extremely economical and scalable classification resolution which will create immediate predictions with low learning value is required. This demand leaves standard batch learning algorithms out of thought. Second, classical classification strategies, be it batch or on-line, typically encounter a quandary once applied to a gaggle of tasks, i.e., on one hand, a single classification model trained on the complete assortment of knowledge from all tasks could fail to capture characteristics of individual task; on the other hand, a model trained severally on individual tasks could suffer from insufficient coaching information. To beat these challenges, during this paper, we tend to propose a cooperative on-line multi-task learning methodology that learns a world model over the complete data of all tasks. We also evaluate it on 3 real-life problems—spam email filtering, bioinformatics information classification, and micro-blog sentiment detection. Experimental results show that our methodology is effective and scalable at the web classification of multiple connected tasks.

Keywords

Artificial Intelligence, Learning Systems, Online Learning, Multi-Task Learning, Classification

How to Cite this Article?

Murugan. A. A, Pradeepa. V, Aishwarya. A, Meena. R and Gayathri. M (2015). Individual and Global Models to Achieve an Overall Improvement for Multi-task Learning. i-manager’s Journal on Information Technology, 4(1), 19-25. https://doi.org/10.26634/jit.4.1.3280

References

[1]. E. V. Bonilla, K. M. Chai, and C. K. I. Williams, (2007). “Multi-task Gaussian process prediction,” in NIPS.
[2]. K. Crammer, O. Dekel, J. Keshet, S. Shalev-Shwartz, and Y. Singer, (2006). “Online passive-aggressive algorithms,” J. Mach. Learn. Res., Vol. 7, pp. 551–585.
[3]. G. Li, K. Chang, S. C. H. Hoi, W. Liu, and R. Jain, (2011). “Collaborative online learning of user generated content,” in Proc. 20th ACM Int. CIKM, pp. 285–290.
[4]. K. Crammer and Y. Singer, (2003). “Ultraconservative online algorithms for multiclass problems,” J. Mach. Learn. Res., Vol. 3, pp. 951–991.
[5]. T. Evgeniou, C. A. Micchelli, and M. Pontil, (2005). “Learning multiple tasks with kernel methods,” J. Mach. Learn. Res., Vol. 6,pp. 615–637.
[6]. L. Jacob, F. Bach, and J. Vert, (2009). “Clustered multitask learning,” in NIPS, pp. 745–752.
[7]. Y. Li and P. M. Long, (1999). “The relaxed online maximum margin algorithm,” in NIPS, pp. 498–504.
[8]. A. Saha, P. Rai, H. Daumé, III, and S. Venkatasubramanian, (2011). “Online learning of multiple tasks and their relationships,” in Proc. 14th Int. Conf. AISTATS, Ft. Lauderdale, FL, USA, , pp. 643–651.
[9]. C. Widmer, Y. Altun, N. C. Toussaint, and G. Rätsch, (2010). “Inferring latent task structure for multi-task learning via multiple kernel learning,” BMC Bioinformatics, Vol. 11, No. 8, p. S5.
[10]. L. Yang, R. Jin, and J. Ye, (2009). “Online learning by ellipsoid method,” in Proc. 26th Annu. ICML, Montreal, QC, Canada, p.145.
If you have access to this article please login to view the article or kindly login to purchase the article

Purchase Instant Access

Single Article

North Americas,UK,
Middle East,Europe
India Rest of world
USD EUR INR USD-ROW
Pdf 35 35 200 20
Online 35 35 200 15
Pdf & Online 35 35 400 25

Options for accessing this content:
  • If you would like institutional access to this content, please recommend the title to your librarian.
    Library Recommendation Form
  • If you already have i-manager's user account: Login above and proceed to purchase the article.
  • New Users: Please register, then proceed to purchase the article.