In this paper, we examine a method for the fusion of ranked data in the context of a Cayley graph. We investigate this Cayley graph model for optimization of fusion by rank combination. We outline a method of data fusion by combination of weighted rankings. Information systems are represented as nodes in a Cayley graph. Our goal is to determine a metric of diversity and performance in this graph in order to build a model for optimizing fusion by rank combination. We use the Kendall distance between nodes in the Cayley graph of the symmetric group Sn as a measure of performance. In doing so we demonstrate that in S6 there is a quadratic relationship between the weights of the fusion of two information systems and the performance of the fusion in our abstract space. From such a relationship we propose a set of functions for extrapolating optimal fusion weights in the symmetric group Sn.
[1]
E. A. Fox,et al.
Combining the Evidence of Multiple Query Representations for Information Retrieval
,
1995,
Inf. Process. Manag..
[2]
Edward A. Fox,et al.
Combination of Multiple Searches
,
1993,
TREC.
[3]
R. Forthofer,et al.
Rank Correlation Methods
,
1981
.
[4]
Paul B. Kantor,et al.
Counter-intuitive Cases of Data Fusion in Information Retrieval.
,
2001
.
[5]
J. Marden.
Analyzing and Modeling Rank Data
,
1996
.
[6]
Ronald Fagin,et al.
Comparing top k lists
,
2003,
SODA '03.
[7]
Garrison W. Cottrell,et al.
Fusion Via a Linear Combination of Scores
,
1999,
Information Retrieval.
[8]
W. Bruce Croft,et al.
Evaluation of an inference network-based retrieval model
,
1991,
TOIS.