Filters








23,727 Hits in 1.7 sec

Attributed Subspace Clustering

Jing Wang, Linchuan Xu, Feng Tian, Atsushi Suzuki, Changqing Zhang, Kenji Yamanishi
2019 Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence  
Therefore, we propose an innovative model called attributed subspace clustering (ASC). It simultaneously learns multiple self-representations on latent representations derived from original data.  ...  Existing methods on representation-based subspace clustering mainly treat all features of data as a whole to learn a single self-representation and get one clustering solution.  ...  In this paper, we propose an innovative representation based subspace clustering approach, called Attributed Subspace Clustering (ASC), which interprets data from different perspectives and obtains multiple  ... 
doi:10.24963/ijcai.2019/516 dblp:conf/ijcai/WangXTSZY19 fatcat:bzwcfw75zzadnpynpbiufx6niq

A Generic Framework for Interesting Subspace Cluster Detection in Multi-attributed Networks [article]

Feng Chen, Baojian Zhou, Adil Alim, Liang Zhao
2018 arXiv   pre-print
In a multi-attributed network, often, a cluster of nodes is only interesting for a subset (subspace) of attributes, and this type of clusters is called subspace clusters.  ...  In this work, we present a generic and theoretical framework for detection of interesting subspace clusters in large multi-attributed networks.  ...  subspace clusters.  ... 
arXiv:1709.05246v2 fatcat:d7da3lpso5gspd2ochkr4ligxe

Efficient approaches for summarizing subspace clusters into k representatives

Guanhua Chen, Xiuli Ma, Dongqing Yang, Shiwei Tang, Meng Shuai, Kunqing Xie
2010 Soft Computing - A Fusion of Foundations, Methodologies and Applications  
A major challenge in subspace clustering is that subspace clustering may generate an explosive number of clusters with high computational complexity, which severely restricts the usage of subspace clustering  ...  Precisely, only the clusters in low-dimensional subspaces are computed and assembled into representative clusters in high-dimensional subspaces.  ...  Especially, a subspace cluster with k attributes can be constructed easily by k subspace clusters with one attribute. 2.  ... 
doi:10.1007/s00500-010-0552-8 fatcat:4zsjooo3lzd7pg4ohsvqfjnoyq

Subspace clustering for high dimensional datasets

G.N.V.G. Sirisha, M. Shashi
2016 International Journal of Advanced Computer Research  
A subspace is a subset of relevant attributes/dimensions that are shared by the members of a cluster.  ...  Even after relevant attribute selection a cluster that is present in a subset of attributes (subspace) may not be discovered when seen in full dimensional space defined by the global set of relevant attributes  ... 
doi:10.19101/ijacr.2016.625012 fatcat:2jcwv5hwcvdw5ojoaznh2mv5gm

Bottom-up evolutionary subspace clustering

Ali Vahdat, Malcolm Heywood, Nur Zincir-Heywood
2010 IEEE Congress on Evolutionary Computation  
The ultimate goal of subspace clustering algorithms is to identify both the subset of attributes supporting a cluster and the location of the cluster in the subspace.  ...  Important properties of the approach are that a standard clustering algorithm is deployed in step one to build the initial lattice of attribute-wise clusters.  ...  The distance between an exemplar and its subspace cluster centroid is defined over the attributes specific to each subspace cluster.  ... 
doi:10.1109/cec.2010.5585962 dblp:conf/cec/VahdatHZ10 fatcat:igivliykqrb6rpkoyihmttohpi

OutRank: ranking outliers in high dimensional data

Emmanuel Muller, Ira Assent, Uwe Steinhausen, Thomas Seidl
2008 2008 IEEE 24th International Conference on Data Engineering Workshop  
High dimensional and heterogeneous (continuous and categorical attributes) data, however, pose a problem for most outlier ranking algorithms.  ...  We introduce a consistent model for different attribute types. Our novel scoring functions transform the analyzed structure of the data to a meaningful ranking.  ...  As clustering in the full space is no longer fea-sible, subspace clustering effectively detects locally relevant attributes (a lower dimensional subspace) for each cluster.  ... 
doi:10.1109/icdew.2008.4498387 dblp:conf/icde/MullerASS08 fatcat:qkvjvneya5fxtd5453ojcx3i5a

Finding non-redundant, statistically significant regions in high dimensional data

Gabriela Moise, Jörg Sander
2008 Proceeding of the 14th ACM SIGKDD international conference on Knowledge discovery and data mining - KDD 08  
Projected and subspace clustering algorithms search for clusters of points in subsets of attributes.  ...  Subspace clustering enumerates clusters of points in all subsets of attributes, typically producing many overlapping clusters.  ...  ACKNOWLEDGMENTS We thank the authors who provided us the code for some projected clustering algorithms. This research was supported by the Alberta Ingenuity Fund, iCORE, and NSERC. 8 .  ... 
doi:10.1145/1401890.1401956 dblp:conf/kdd/MoiseS08 fatcat:ibewzzewhngp3khg7zq5ewxxoy

Finding Hierarchies of Subspace Clusters [chapter]

Elke Achtert, Christian Böhm, Hans-Peter Kriegel, Peer Kröger, Ina Müller-Gorman, Arthur Zimek
2006 Lecture Notes in Computer Science  
Those clusters are also called subspace clusters.  ...  In this paper, we propose the algorithm HiSC (Hierarchical Subspace Clustering) that can detect hierarchies of nested subspace clusters, i.e. the relationships of lowerdimensional subspace clusters that  ...  We will refer to a subspace cluster associated to a λ-dimensional projection/subspace (i.e. spanned by λ attributes) as a λ-dimensional subspace cluster.  ... 
doi:10.1007/11871637_42 fatcat:mef5loxk3bh3ncfybu4iv654ze

A subspace filter supporting the discovery of small clusters in very noisy datasets

Frank Höppner
2014 Proceedings of the 26th International Conference on Scientific and Statistical Database Management - SSDBM '14  
A new subspace filter approach is presented that is capable of coping with the difficult situation of finding small clusters embedded in a very noisy environment (more noise than clustering data), which  ...  Feature selection becomes crucial when exploring high-dimensional datasets via clustering, because it is unlikely that the data groups jointly in all dimensions but clustering algorithms treat all attributes  ...  into the clustering algorithm itself (subspace clustering).  ... 
doi:10.1145/2618243.2618260 dblp:conf/ssdbm/Hoppner14 fatcat:q3j3falnlrhzbgpafr4kwojzui

Clustering in applications with multiple data sources—A mutual subspace clustering approach

Ming Hua, Jian Pei
2012 Neurocomputing  
The density-based model identifies dense regions in subspaces as clusters.  ...  In this paper, we study a novel problem of mining mutual subspace clusters from multiple sources. We develop two interesting models and the corresponding methods for mutual subspace clustering.  ...  For a cluster mutual in a clinical subspace and a genomic subspace, we can use the genomic attributes to verify and justify the clinical attributes.  ... 
doi:10.1016/j.neucom.2011.08.032 fatcat:eykfl6t7azb4jfre3ai73hpwei

Ranking outlier nodes in subspaces of attributed graphs

E. Muller, P. I. Sanchez, Y. Mulle, K. Bohm
2013 2013 IEEE 29th International Conference on Data Engineering Workshops (ICDEW)  
Subspace clustering provides a selected subset of nodes and its relevant attributes in which deviation of nodes can be observed.  ...  In this work, we propose a first approach for outlier ranking in subspaces of attributed graphs. We rank graph nodes according to their degree of deviation in both graph and attribute properties.  ...  We abstract from their individual properties and assume that a clustering result is given as follows: Definition 2: Subspace Clustering Result A subspace clustering result in an attributed graph is a set  ... 
doi:10.1109/icdew.2013.6547453 dblp:conf/icde/MullerSMB13 fatcat:uytc7sxwlfgutp7jjvv66zvwoq

Rough subspace-based clustering ensemble for categorical data

Can Gao, Witold Pedrycz, Duoqian Miao
2013 Soft Computing - A Fusion of Foundations, Methodologies and Applications  
Based on the theory of rough sets, the attributes of categorical data are decomposed into a number of rough subspaces.  ...  A novel clustering ensemble algorithm based on rough subspaces is then proposed to deal with categorical data.  ...  Instead of single attribute subspace and random attribute subspace presented in Al-Razgan et al. (2008) and He et al. (2005) , we propose a relevant subspace-based clustering ensemble algorithm for  ... 
doi:10.1007/s00500-012-0972-8 fatcat:ahq3ghmaqbbvfbow3z3afhy6hq

Projected Clustering Using Particle Swarm Optimization

Satish Gajawada, Durga Toshniwal
2012 Procedia Technology - Elsevier  
Points may be assigned to multiple subspace clusters by subspace clustering methods. Projected clustering is preferable to subspace clustering when partition of points is required.  ...  Projected clustering methods output subspace clusters where one point in the dataset belongs to only one subspace cluster.  ...  Neighbourhood points are then used for identifying relevant attributes for subspace clusters. Points are assigned to centers using relevant attributes found.  ... 
doi:10.1016/j.protcy.2012.05.055 fatcat:mpeumbtq3bgilge5sqskd3t4pe

Clustering Algorithms For High Dimensional Data – A Survey Of Issues And Existing Approaches

B.Hari Babu, N.Subash Chandra, T. Venu Gopal
2013 International Journal of Computer Science and Informatics  
The performance issues of the data clustering in high dimensional data it is necessary to study issues like dimensionality reduction, redundancy elimination, subspace clustering, co-clustering and data  ...  Clustering is the most prominent data mining technique used for grouping the data into clusters based on distance measures.  ...  CLIQUE-Clustering in QUEst [13] , is the fundamental algorithm used for numerical attributes for subspace clustering. It starts with a unit elementary rectangular cell in a subspace.  ... 
doi:10.47893/ijcsi.2013.1108 fatcat:ortfep7hw5a6rhqrhgg7cfrbxm

Clustering High Dimensional Data Using Subspace and Projected Clustering Algorithms

Rahmat Widia Sembiring, Jasni Mohamad Zain, Abdullah Embong
2010 International Journal of Computer Science & Information Technology (IJCSIT)  
Subspace clustering enumerates clusters of objects in all subspaces of a dataset. It tends to produce many over lapping clusters.  ...  points and relevant attributes found.  ...  STATPC outperforms previously proposed projected and subspace clustering algorithms in the accuracy of both cluster points and relevant attributes found [5] .  ... 
doi:10.5121/ijcsit.2010.2414 fatcat:dtryyaqfnnckhi7ej72fs2p7q4
« Previous Showing results 1 — 15 out of 23,727 results