Huici, Daniel; Rodríguez, Ricardo J.; Mena, Eduardo
APOTHEOSIS: An efficient approximate similarity search system Journal Article
In: SoftwareX, vol. 29, pp. 102016, 2025, ISSN: 2352-7110.
Abstract | Links | BibTeX | Tags: Approximate K-nearest neighbors, Approximate matching, Approximate search methods, Data similarity analysis, similarity digest algorithms
@article{HuiciRM-SoftX-25,
title = {APOTHEOSIS: An efficient approximate similarity search system},
author = {Daniel Huici and Ricardo J. Rodríguez and Eduardo Mena},
url = {https://webdiis.unizar.es/~ricardo/files/papers/HuiciRM-SoftX-25.pdf},
doi = {10.1016/j.softx.2024.102016},
issn = {2352-7110},
year = {2025},
date = {2025-02-01},
urldate = {2025-02-01},
journal = {SoftwareX},
volume = {29},
pages = {102016},
abstract = {APOTHEOSIS is a tool for efficiently identifying and comparing data similarity in large datasets, addressing challenges faced by traditional methods such as scalability and speed. APOTHEOSIS overcomes them by combining advanced algorithms and data structures, enabling fast and accurate similarity analysis. Specifically, it uses a custom hierarchical small navigation world as an approximate $K$-nearest neighbors search method, and approximate similarity digests algorithms to find common features between similar data items, also supporting various distance metrics beyond vector-based approaches. Our software tool is designed for seamless integration into research workflows, improving reproducibility and facilitating the comparison of large-scale, high-dimensional data comparison across multiple domains.},
keywords = {Approximate K-nearest neighbors, Approximate matching, Approximate search methods, Data similarity analysis, similarity digest algorithms},
pubstate = {published},
tppubtype = {article}
}
APOTHEOSIS is a tool for efficiently identifying and comparing data similarity in large datasets, addressing challenges faced by traditional methods such as scalability and speed. APOTHEOSIS overcomes them by combining advanced algorithms and data structures, enabling fast and accurate similarity analysis. Specifically, it uses a custom hierarchical small navigation world as an approximate $K$-nearest neighbors search method, and approximate similarity digests algorithms to find common features between similar data items, also supporting various distance metrics beyond vector-based approaches. Our software tool is designed for seamless integration into research workflows, improving reproducibility and facilitating the comparison of large-scale, high-dimensional data comparison across multiple domains.