@inproceedings{6186ee85b0c446088a5a344b3e70f17e,
title = "A summarization paradigm for big data",
abstract = "We have developed an efficient summarization paradigm for data drawn from hierarchical domain to construct a succinct view of important large-valued regions ('heavy hitters'). It requires one pass over the data with moderate number of updates per element of the data and requires lesser amount of memory space as compared to existing approaches for approximating hierarchically discounted frequency counts of heavy hitters with provable guarantees. The proposed technique is generic that can make use of existing state-of-the-art sketch-based or count-based frequency estimation approaches. Any algorithm from both of these families can be coupled as a subroutine in the proposed framework without any substantial modifications. Experimental as well as theoretical justifications have been provided for its significance.",
keywords = "Big Data, Data Summarization, Hierarchical Heavy Hitters",
author = "Zubair Shah and Mahmood, {Abdun Naser}",
note = "Publisher Copyright: {\textcopyright} 2014 IEEE.; 2nd IEEE International Conference on Big Data, IEEE Big Data 2014 ; Conference date: 27-10-2014 Through 30-10-2014",
year = "2014",
doi = "10.1109/BigData.2014.7004494",
language = "English",
series = "Proceedings - 2014 IEEE International Conference on Big Data, IEEE Big Data 2014",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "61--63",
editor = "Jimmy Lin and Jian Pei and Hu, {Xiaohua Tony} and Wo Chang and Raghunath Nambiar and Charu Aggarwal and Nick Cercone and Vasant Honavar and Jun Huan and Bamshad Mobasher and Saumyadipta Pyne",
booktitle = "Proceedings - 2014 IEEE International Conference on Big Data, IEEE Big Data 2014",
address = "United States",
}