Scalability Comparison of Peer-to-Peer Similarity Search Structures

BATKO, Michal, David NOVÁK, Fabrizio FALCHI and Pavel ZEZULA. Scalability Comparison of Peer-to-Peer Similarity Search Structures. Future Generation Computer Systems. Amsterdam, The Netherlands: Elsevier Science, 2008, vol. 24, No 8, p. 834-848. ISSN 0167-739X.

Basic information

Original name

Scalability Comparison of Peer-to-Peer Similarity Search Structures

Name in Czech

Porovnání škálovatelnosti peer-to-peer struktur pro podobnostní vyhledávání

Authors

BATKO, Michal (203 Czech Republic, belonging to the institution), David NOVÁK (203 Czech Republic, guarantor, belonging to the institution), Fabrizio FALCHI (380 Italy) and Pavel ZEZULA (203 Czech Republic, belonging to the institution)

Edition

Future Generation Computer Systems, Amsterdam, The Netherlands, Elsevier Science, 2008, 0167-739X

---

Other information

Language

English

Type of outcome

Článek v odborném periodiku

Field of Study

10201 Computer sciences, information science, bioinformatics

Country of publisher

Netherlands

Confidentiality degree

není předmětem státního či obchodního tajemství

References:

DOI identifier of the paper

Impact factor

Impact factor: 1.476

RIV identification code

RIV/00216224:14330/08:00024131

Organization unit

Faculty of Informatics

UT WoS

000258426100008

Keywords in English

Similarity search; Scalability; Metric space; Distributed index structures; Peer-to-Peer networks

Tags

DISA, Distributed index structures, Metric Space, Peer-to-Peer Networks, scalability, similarity search

Tags

International impact, Reviewed

---

Abstract

V originále

Due to the increasing complexity of current digital data, similarity search has become a fundamental computational task in many applications. Unfortunately, its costs are still high and grow linearly on single server structures, which prevents them from efficient application on large data volumes. In this paper, we shortly describe four recent scalable distributed techniques for similarity search and study their performance in executing queries on three different datasets. Though all the methods employ parallelism to speed up query execution, different advantages for different objectives have been identified by experiments. The reported results would be helpful for choosing the best implementations for specific applications. They can also be used for designing new and better indexing structures in the future.

In Czech

Kvůli rostoucí složitosti současných digitálních dat se stalo podobnostní vyhledávání základním výpočetním úkolem v mnoha aplikacích. V tomto článku krátce popisujeme čtyři škálovatelné distribuované techniky pro podobnostní vyhledávání a studujeme jejich výkon při vyhodnocování dotazů na různých datových množinách.

---

Links

GD102/05/H050, research and development project	Name: Integrovaný přístup k výchově studentů DSP v oblasti paralelních a distribuovaných systémů Investor: Czech Science Foundation, Integrated approach to education of PhD students in the area of parallel and distributed systems
1ET100300419, research and development project	Name: Inteligentní modely, algoritmy, metody a nástroje pro vytváření sémantického webu Investor: Academy of Sciences of the Czech Republic, Intelligent Models, Algorithms, Methods and Tools for the Semantic Web (realization)