Towards Personalized Similarity Search for Vector Databases

D 2024

Towards Personalized Similarity Search for Vector Databases

MAHRÍK, Marek, Matúš ŠIKYŇA, Vladimír MÍČ a Pavel ZEZULA

Základní údaje

Originální název

Towards Personalized Similarity Search for Vector Databases

Autoři

MAHRÍK, Marek, Matúš ŠIKYŇA, Vladimír MÍČ a Pavel ZEZULA

Vydání

Cham, 17th International Conference on Similarity Search and Applications (SISAP 2024), od s. 126-139, 14 s. 2024

Nakladatel

Springer

Další údaje

Jazyk

angličtina

Typ výsledku

Stať ve sborníku

Obor

10200 1.2 Computer and information sciences

Stát vydavatele

Švýcarsko

Utajení

není předmětem státního či obchodního tajemství

Forma vydání

tištěná verze "print"

Organizační jednotka

Fakulta informatiky

ISBN

978-3-031-75822-5

DOI

http://dx.doi.org/10.1007/978-3-031-75823-2_11

Klíčová slova anglicky

Similarity search;Personalized similarity;Vector databases

Štítky

DISA, similarity search

Příznaky

Mezinárodní význam, Recenzováno

Změněno: 31. 10. 2024 22:21, Mgr. et Mgr. Matúš Šikyňa

Anotace

V originále

The importance of similarity search has become prominent in the fast-evolving vector databases, which apply content embedding techniques on complex data to produce and manage large collections of high-dimensional vectors. Processing of such data is only possible by using a similarity function for storage, structure, and retrieval. However, if multiple users access the collection, their views on similarity can differ as similarity, in general, is subjective and context-dependent. In this article, we elaborate on the problem of a similarity search engine implementation, where users use a common index but search with personalised views of similarity, implemented by a possibly different similarity model. Specifically, we define a foundational theoretical framework and conduct experiments on real-life data to confirm the viability of such an approach. The experiments also indicate future research directions needed to propose and implement an effective and efficient personalised similarity search engine.

Návaznosti

MUNI/A/1590/2023, interní kód MU

Název: Využití technik umělé inteligence pro zpracování dat, komplexní analýzy a vizualizaci rozsáhlých dat

Investor: Masarykova univerzita, Využití technik umělé inteligence pro zpracování dat, komplexní analýzy a vizualizaci rozsáhlých dat

Citovat

MAHRÍK, Marek, Matúš ŠIKYŇA, Vladimír MÍČ a Pavel ZEZULA. Towards Personalized Similarity Search for Vector Databases. In 17th International Conference on Similarity Search and Applications (SISAP 2024). Cham: Springer, 2024, s. 126-139. ISBN 978-3-031-75822-5. Dostupné z: https://dx.doi.org/10.1007/978-3-031-75823-2_11.

@inproceedings{2429637,
   author = {Mahrík, Marek and Šikyňa, Matúš and Míč, Vladimír and Zezula, Pavel},
   address = {Cham},
   booktitle = {17th International Conference on Similarity Search and Applications (SISAP 2024)},
   doi = {http://dx.doi.org/10.1007/978-3-031-75823-2_11},
   keywords = {Similarity search;Personalized similarity;Vector databases},
   howpublished = {tištěná verze "print"},
   language = {eng},
   location = {Cham},
   isbn = {978-3-031-75822-5},
   pages = {126-139},
   publisher = {Springer},
   title = {Towards Personalized Similarity Search for Vector Databases},
   year = {2024}
}

TY  - JOUR
ID  - 2429637
AU  - Mahrík, Marek - Šikyňa, Matúš - Míč, Vladimír - Zezula, Pavel
PY  - 2024
TI  - Towards Personalized Similarity Search for Vector Databases
PB  - Springer
CY  - Cham
SN  - 9783031758225
KW  - Similarity search;Personalized similarity;Vector databases
N2  - The importance of similarity search has become prominent in the fast-evolving vector databases, which apply content embedding techniques on complex data to produce and manage large collections of high-dimensional vectors. Processing of such data is only possible by using a similarity function for storage, structure, and retrieval. However, if multiple users access the collection, their views on similarity can differ as similarity, in general, is subjective and context-dependent. In this article, we elaborate on the problem of a similarity search engine implementation, where users use a common index but search with personalised views of similarity, implemented by a possibly different similarity model. Specifically, we define a foundational theoretical framework and conduct experiments on real-life data to confirm the viability of such an approach. The experiments also indicate future research directions needed to propose and implement an effective and efficient personalised similarity search engine.
ER  -

MAHRÍK, Marek, Matúš ŠIKYŇA, Vladimír MÍČ a Pavel ZEZULA. Towards Personalized Similarity Search for Vector Databases. In \textit{17th International Conference on Similarity Search and Applications (SISAP 2024)}. Cham: Springer, 2024, s.~126-139. ISBN~978-3-031-75822-5. Dostupné z: https://dx.doi.org/10.1007/978-3-031-75823-2\_{}11.

Podrobný výpis o publikaci