@inproceedings{0e4bf01f463a4c50a4f9f3952cca3de9,
title = "Applying Compression to Hierarchical Clustering",
abstract = "Hierarchical Clustering is widely used in Machine Learning and Data Mining. It stores bit-vectors in the nodes of a k-ary tree, usually without trying to compress them. We suggest a data compression application of hierarchical clustering with a double usage of the xoring operations defining the Hamming distance used in the clustering process, extending it also to be used to transform the vector in one node into a more compressible form, as a function of the vector in the parent node. Compression is then achieved by run-length encoding, followed by optional Huffman coding, and we show how the compressed file may be processed directly, without decompression.",
author = "Gilad Baruch and Klein, \{Shmuel Tomi\} and Dana Shapira",
note = "Publisher Copyright: {\textcopyright} 2018, Springer Nature Switzerland AG.; 11th International Conference on Similarity Search and Applications, SISAP 2018 ; Conference date: 07-10-2018 Through 09-10-2018",
year = "2018",
doi = "10.1007/978-3-030-02224-2\_12",
language = "الإنجليزيّة",
isbn = "9783030022235",
series = "Lecture Notes in Computer Science (including subseries Lecture Notes in Artificial Intelligence and Lecture Notes in Bioinformatics)",
publisher = "Springer Verlag",
pages = "151--162",
editor = "St{\'e}phane Marchand-Maillet and Silva, \{Yasin N.\} and Edgar Ch{\'a}vez",
booktitle = "Similarity Search and Applications - 11th International Conference, SISAP 2018, Proceedings",
address = "ألمانيا",
}