DocumentCode :
679559
Title :
On Anomalous Hotspot Discovery in Graph Streams
Author :
Weiren Yu ; Aggarwal, Charu C. ; Shuai Ma ; Haixun Wang
Author_Institution :
SKLSDE Lab., Beihang Univ., Beijing, China
fYear :
2013
fDate :
7-10 Dec. 2013
Firstpage :
1271
Lastpage :
1276
Abstract :
Network streams have become ubiquitous in recent years because of many dynamic applications. Such streams may show localized regions of activity and evolution because of anomalous events. This paper will present methods for dynamically determining anomalous hot spots from network streams. These are localized regions of sudden activity or change in the underlying network. We will design a localized principal component analysis algorithm, which can continuously maintain the information about the changes in the different neighborhoods of the network. We will use a fast incremental eigenvector update algorithm based on von Mises iterations in a lazy way in order to efficiently maintain local correlation information. This is used to discover local change hotspots in dynamic streams. We will finally present an experimental study to demonstrate the effectiveness and efficiency of our approach.
Keywords :
eigenvalues and eigenfunctions; graph theory; network theory (graphs); principal component analysis; anomalous events; anomalous hotspot discovery; dynamic applications; dynamic streams; fast incremental eigenvector update algorithm; graph streams; local change hotspot discovery; local correlation information; localized principal component analysis algorithm; network streams; von Mises iterations; Algorithm design and analysis; Correlation; Eigenvalues and eigenfunctions; Image edge detection; Motion pictures; Time-frequency analysis; Vectors; anomaly detection; graph streams;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Data Mining (ICDM), 2013 IEEE 13th International Conference on
Conference_Location :
Dallas, TX
ISSN :
1550-4786
Type :
conf
DOI :
10.1109/ICDM.2013.32
Filename :
6729633
Link To Document :
بازگشت