Fast Tuning the Index Construction Parameters of Proximity Graphs in Vector Databases

2026-02-12

AI Summary

This work addresses the inefficiency of parameter tuning in proximity graph index construction, which has become a performance bottleneck in vector databases due to the repeated cycles of graph building and evaluation. To this end, we propose FastPGT, the first framework to systematically optimize this process. FastPGT accelerates tuning by enabling parallel construction of multiple graphs to minimize redundant computation, enhances existing state-of-the-art parameter recommendation models to support batched parameter suggestions, and integrates an efficient k-ANNS evaluation mechanism for synergistic speedup. Experimental results on real-world datasets demonstrate that FastPGT achieves up to 2.37× speedup over the current state-of-the-art method, VDTuner, while preserving tuning quality.

Technology Category

• Search and Optimization: Distributed Search
• Machine Learning: Graph-based Machine Learning
• Data Mining & Knowledge Management: Graph Mining, Social Network Analysis & Community

Application Category

• Graph Algorithms and Modeling for the Web: Querying, indexing, and retrieval in Web-related graphs
• Search and Retrieval-Augmented AI: Efficiency and scalability of Web search engines
• User Modeling, Personalization and Recommendation: Federated recommendation systems and personalization

Abstract

k-approximate nearest neighbor search (k-ANNS) in high-dimensional vector spaces is a fundamental problem across many fields. With the advent of vector databases and retrieval-augmented generation, k-ANNS has garnered increasing attention. Among existing methods, proximity graphs (PG) based approaches are the state-of-the-art (SOTA) methods. However, the construction parameters of PGs significantly impact their search performance. Before constructing a PG for a given dataset, it is essential to tune these parameters, which first recommends a set of promising parameters and then estimates the quality of each parameter by building the corresponding PG and then testing its k-ANNS performance. Given that the construction complexity of PGs is superlinear, building and evaluating graph indexes accounts for the primary cost of parameter tuning. Unfortunately, there is currently no method considered and optimized this process.In this paper, we introduce FastPGT, an efficient framework for tuning the PG construction parameters. FastPGT accelerates parameter estimation by building multiple PGs simultaneously, thereby reducing repeated computations. Moreover, we modify the SOTA tuning model to recommend multiple parameters at once, which can be efficiently estimated using our method of building multiple PGs simultaneously. Through extensive experiments on real-world datasets, we demonstrate that FastPGT achieves up to 2.37x speedup over the SOTA method VDTuner, without compromising tuning quality.

Problem

• k-approximate nearest neighbor search
• proximity graphs
• parameter tuning
• vector databases
• index construction

Innovation

• proximity graphs
• parameter tuning
• vector databases
• k-ANNS
• FastPGT