Annoy (Approximate Nearest Neighbors Oh Yeah) Library

From GM-RKB
Jump to navigation Jump to search

A Annoy (Approximate Nearest Neighbors Oh Yeah) Library is an approximate nearest neighbors search software library that supports high-dimensional spaces.

References

2024

2020

  • (Aumüller et al., 2020) ⇒ Martin Aumüller, Erik Bernhardsson, and Alexander Faithfull. (2020). “ANN-Benchmarks: A benchmarking tool for approximate nearest neighbor algorithms.” In: Information Systems, 87: 101374.
    • NOTE: It presents a comprehensive system for benchmarking approximate nearest neighbor algorithms, showcasing the effectiveness of Annoy in comparison to other algorithms for high recall values and emphasizing the significance of implementation decisions on algorithm performance.

2017

  • (Aumüller et al., 2017) ⇒ Martin Aumüller, Erik Bernhardsson, and Alexander Faithfull. (2017). “ANN-benchmarks: A benchmarking tool for approximate nearest neighbor algorithms.” In: International conference on similarity search and applications, pp. 34-49. Cham: Springer International Publishing.
    • NOTE: It details the performance of various approximate nearest neighbor algorithms, including Annoy, during high recall value tasks, and highlights the impact of specific implementation decisions on the efficiency of these algorithms.