Combination skyline queries

  • Authors:

  • Xi Guo;Chuan Xiao;Yoshiharu Ishikawa

  • Affiliations:

  • Graduate School of Information Science, Nagoya University, Japan;Information Technology Center, Nagoya University, Japan;Information Technology Center, Nagoya University, Japaraduate School of Information Science, Nagoya University, Japan, National Institute of Informatics, Japan

  • Venue:
  • Transactions on Large-Scale Data- and Knowledge-Centered Systems VI
  • Year:
  • 2012

Quantified Score

Hi-index 0.00

Visualization

Abstract

Given a collection of data objects, the skyline problem is to select the objects which are not dominated by any others. In this paper, we propose a new variation of the skyline problem, called the combination skyline problem. The goal is to find the fixed-size combinations of objects which are skyline among all possible combinations. Our problem is technically challenging as traditional skyline approaches are inapplicable to handle a huge number of possible combinations. By indexing objects with an R-tree, our solution is based on object-selecting patterns that indicate the number of objects to be selected for each MBR. We develop two major pruning conditions to avoid unnecessary expansions and enumerations, as well as a technique to reduce space consumption on storing the skyline for each rule in the object-selecting pattern. The efficiency of the proposed algorithm is demonstrated by extensive experiments on both real and synthetic datasets.