$k$ -most diverse items from a result set. Whereas previous research has mainly considered the static version of the problem, in this paper, we exploit the dynamic case in which the result set changes over time, as for example, in the case of notification services. We define the CONTINUOUS $k$ -DIVERSITY PROBLEM along with appropriate constraints that enforce continuity requirements on the diversified results. Our proposed approach is based on cover trees and supports dynamic item insertion and deletion. The diversification problem is in general NP-hard; we provide theoretical bounds that characterize the quality of our cover tree solution with respect to the optimal one. Since results are often associated with a relevance score, we extend our approach to account for relevance. Finally, we report experimental results concerning the efficiency and effectiveness of our approach on a variety of real and synthetic datasets." /> $k$ -most diverse items from a result set. Whereas previous research has mainly considered the static version of the problem, in this paper, we exploit the dynamic case in which the result set changes over time, as for example, in the case of notification services. We define the CONTINUOUS $k$ -DIVERSITY PROBLEM along with appropriate constraints that enforce continuity requirements on the diversified results. Our proposed approach is based on cover trees and supports dynamic item insertion and deletion. The diversification problem is in general NP-hard; we provide theoretical bounds that characterize the quality of our cover tree solution with respect to the optimal one. Since results are often associated with a relevance score, we extend our approach to account for relevance. Finally, we report experimental results concerning the efficiency and effectiveness of our approach on a variety of real and synthetic datasets." /> $k$ -most diverse items from a result set. Whereas previous research has mainly considered the static version of the problem, in this paper, we exploit the dynamic case in which the result set changes over time, as for example, in the case of notification services. We define the CONTINUOUS $k$ -DIVERSITY PROBLEM along with appropriate constraints that enforce continuity requirements on the diversified results. Our proposed approach is based on cover trees and supports dynamic item insertion and deletion. The diversification problem is in general NP-hard; we provide theoretical bounds that characterize the quality of our cover tree solution with respect to the optimal one. Since results are often associated with a relevance score, we extend our approach to account for relevance. Finally, we report experimental results concerning the efficiency and effectiveness of our approach on a variety of real and synthetic datasets." /> Diverse Set Selection Over Dynamic Data
Subscribe
Issue No.05 - May (2014 vol.26)
pp: 1102-1116
Marina Drosou , Comput. Sci. Dept., Univ. of Ioannina, Ioannina, Greece
Evaggelia Pitoura , Comput. Sci. Dept., Univ. of Ioannina, Ioannina, Greece
ABSTRACT
Result diversification has recently attracted considerable attention as a means of increasing user satisfaction in recommender systems, as well as in web and database search. In this paper, we focus on the problem of selecting the k-most diverse items from a result set. Whereas previous research has mainly considered the static version of the problem, in this paper, we exploit the dynamic case in which the result set changes over time, as for example, in the case of notification services. We define the CONTINUOUS k-DIVERSITY PROBLEM along with appropriate constraints that enforce continuity requirements on the diversified results. Our proposed approach is based on cover trees and supports dynamic item insertion and deletion. The diversification problem is in general NP-hard; we provide theoretical bounds that characterize the quality of our cover tree solution with respect to the optimal one. Since results are often associated with a relevance score, we extend our approach to account for relevance. Finally, we report experimental results concerning the efficiency and effectiveness of our approach on a variety of real and synthetic datasets.
INDEX TERMS
tree data structures, computational complexity, database management systems, human factors, information filtering, Internet, optimisation, recommender systems,indexing methods, user satisfaction, recommender systems, database search, k-most diverse item selection, continuous k-diversity problem, continuity requirements, dynamic item insertion, dynamic item deletion, NP-hard diversification problem, cover tree solution, synthetic datasets, real datasets, information filtering,Heuristic algorithms, Diversity reception, Approximation algorithms, Silicon, Complexity theory, Indexes, Computational modeling,Selection process, Information Technology and Systems, Database Management, Physical Design, Database Applications, Information Storage and Retrieval, Information Search and Retrieval, Information filtering,similarity measures, Indexing methods, selection process, information filtering, search process
CITATION
Marina Drosou, Evaggelia Pitoura, "Diverse Set Selection Over Dynamic Data", IEEE Transactions on Knowledge & Data Engineering, vol.26, no. 5, pp. 1102-1116, May 2014, doi:10.1109/TKDE.2013.44