Reference : Clustering-Based Anomaly Detection in Multi-View Data
Scientific congresses and symposiums : Paper published in a book
Engineering, computing & technology : Computer science
Clustering-Based Anomaly Detection in Multi-View Data
Marcos Alvarez, Alejandro mailto [Université de Liège - ULiège > Dép. d'électric., électron. et informat. (Inst.Montefiore) > Systèmes et modélisation >]
Yamada, Makoto [Yahoo! Inc. > Yahoo! Labs > Search Science & Anti-Abuse Team > >]
Kimura, Akisato [NTT Corporation > Media Information Laboratory > Media Recognition Research Group > >]
Iwata, Tomoharu [NTT Corporation > Communication Science Laboratories > Learning and Intelligent Systems Research Group > >]
Proceedings of the 22nd International Conference on Information and Knowledge Management
New York
ACM International Conference on Information and Knowledge Management (CIKM 2013)
from 27-10-2013 to 01-11-2013
San Francisco
[en] anomaly detection ; multi-view data ; affinity propagation
[en] This paper proposes a simple yet effective anomaly detection method for multi-view data. The proposed approach detects anomalies by comparing the neighborhoods in different views. Specifically, clustering is performed separately in the different views and affinity vectors are derived for each object from the clustering results. Then, the anomalies are detected by comparing affinity vectors in the multiple views. An advantage of the proposed method over existing methods is that the tuning parameters can be determined effectively from the given data. Through experiments on synthetic and benchmark datasets, we show that the proposed method outperforms existing methods.

File(s) associated to this reference

Fulltext file(s):

Open access
cikm2013.pdfPublisher postprint300.19 kBView/Open

Bookmark and Share SFX Query

All documents in ORBi are protected by a user license.