Recent Approaches and Trends in Approximate Nearest Neighbor Search, with Remarks on Benchmarking.

M Aumüller, M Ceccarello - IEEE Data Eng. Bull., 2023 - sites.computer.org
Nearest neighbor search is a computational primitive whose efficiency is paramount to many
applications. As such, the literature recently blossomed with many works focusing on …

TabReD: Analyzing Pitfalls and Filling the Gaps in Tabular Deep Learning Benchmarks

I Rubachev, N Kartashev, Y Gorishniy… - arxiv preprint arxiv …, 2024 - arxiv.org
Advances in machine learning research drive progress in real-world applications. To ensure
this progress, it is important to understand the potential pitfalls on the way from a novel …

Locally-Adaptive Quantization for Streaming Vector Search

C Aguerrebere, M Hildebrand, IS Bhati, T Willke… - arxiv preprint arxiv …, 2024 - arxiv.org
Retrieving the most similar vector embeddings to a given query among a massive collection
of vectors has long been a key component of countless real-world applications. The recently …

Lossless Compression of Vector IDs for Approximate Nearest Neighbor Search

D Severo, G Ottaviano, M Muckley, K Ullrich… - arxiv preprint arxiv …, 2025 - arxiv.org
Approximate nearest neighbor search for vectors relies on indexes that are most often
accessed from RAM. Therefore, storage is the factor limiting the size of the database that can …

Incremental IVF Index Maintenance for Streaming Vector Search

J Mohoney, A Pacaci, SR Chowdhury… - arxiv preprint arxiv …, 2024 - arxiv.org
The prevalence of vector similarity search in modern machine learning applications and the
continuously changing nature of data processed by these applications necessitate efficient …

Dynamic Exploration Graph: A Novel Approach for Efficient Nearest Neighbor Search in Evolving Multimedia Datasets

N Hezel, KU Barthel, B Schilling, K Schall… - … Conference on Multimedia …, 2025 - Springer
Abstract Approximate Nearest Neighbor Search (ANNS) represents a fundamental problem
in various applications (image-search, recommendation systems). While graph-based …

On the Scalability and Efficiency of Graph Processing Systems

X Yin - 2024 - search.proquest.com
UNIVERSITY OF CALIFORNIA RIVERSIDE On the Scalability and Efficiency of Graph
Processing Systems A Dissertation submitted in par Page 1 UNIVERSITY OF CALIFORNIA …