Abstract | ||
---|---|---|
We present a clustering and indexing paradigm (called Clindex) for high-dimensional search spaces. The scheme is designed for approximate similarity searches, where one would like to find many of the data points near a target point, but where one can tolerate missing a few near points. For such searches, our scheme can find near points with high recall in very few IOs and perform significantly better than other approaches. Our scheme is based on finding clusters and, then, building a simple but efficient index for them. We analyze the trade-offs involved in clustering and building such an index structure, and present extensive experimental results |
Year | DOI | Venue |
---|---|---|
2002 | 10.1109/TKDE.2002.1019214 | IEEE Trans. Knowl. Data Eng. |
Keywords | Field | DocType |
present extensive experimental result,pattern clustering,time complexity,high-dimensional search space,experimental results,index structure,tree data structures,visual databases,clindex,target point,efficient index,approximate similarity search,indexing,near point,database indexing,high-dimensional spaces,high recall,computational complexity,multidimensional indexes.,data point,similarity search,indexing paradigm,tree-like index structures,high-dimensional search spaces,very large databases,image database,large databases,query processing,clustering,search space,indexation | Data point,Data mining,Correlation clustering,Computer science,Tree (data structure),Search engine indexing,Cluster analysis,Database index,Nearest neighbor search,Computational complexity theory | Journal |
Volume | Issue | ISSN |
14 | 4 | 1041-4347 |
Citations | PageRank | References |
69 | 5.26 | 40 |
Authors | ||
4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Chen Li | 1 | 2816 | 196.16 |
Edward Y. Chang | 2 | 4519 | 336.59 |
Héctor García-Molina | 3 | 24359 | 5652.13 |
Gio Wiederhold | 4 | 4260 | 1502.89 |