An Iterative Distance-Based Model for Unsupervised Weighted Rank Aggregation

Rank aggregation is a popular problem that combines different ranked lists from various sources (frequently called voters or judges), and generates a single aggregated list with improved ranking of its items. In this context, a portion of the existing methods attempt to address the problem by treati...

Full description

Saved in:
Bibliographic Details
Published in:2019 IEEE WIC ACM International Conference on Web Intelligence (WI) pp. 358 - 362
Main Authors: Akritidis, Leonidas, Fevgas, Athanasios, Bozanis, Panayiotis
Format: Conference Proceeding
Language:English
Published: New York, NY, USA ACM 14.10.2019
Series:ACM Other Conferences
Subjects:
Computational modeling
Computing methodologies
Computing methodologies > Machine learning
Convergence
distance-based
Information systems
Information systems > Information retrieval
Information systems > Information retrieval > Retrieval models and ranking
Information systems > Information retrieval > Retrieval tasks and goals
Information systems > Information systems applications
Iterative methods
Kernel
Logic gates
Measurement
rank aggregation
Unsupervised learning
unsupervised rank aggregation
weighted rank aggregation
unsupervised rank aggregation
weighted rank aggregation
distance-based
rank aggregation
unsupervised learning
ISBN:1450369340, 9781450369343
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Rank aggregation is a popular problem that combines different ranked lists from various sources (frequently called voters or judges), and generates a single aggregated list with improved ranking of its items. In this context, a portion of the existing methods attempt to address the problem by treating all voters equally. Nevertheless, several related works proved that the careful and effective assignment of different weights to each voter leads to enhanced performance. In this article, we introduce an unsupervised algorithm for learning the weights of the voters for a specific topic or query. The proposed method is based on the fact that if a voter has submitted numerous elements which have been placed in high positions in the aggregated list, then this voter should be treated as an expert, compared to the voters whose suggestions appear in lower places or do not appear at all. The algorithm iteratively computes the distance of each input list with the aggregated list and modifies the weights of the voters until all weights converge. The effectiveness of the proposed method is experimentally demonstrated by aggregating input lists from six TREC conferences.
ISBN:1450369340
9781450369343
DOI:10.1145/3350546.3352547