A Comprehensive Survey on Vector Database: Storage and Retrieval Technique, Challenge

📅 2023-10-18
🏛️ arXiv.org
📈 Citations: 62
Influential: 3
📄 PDF

career value

241K/year
🤖 AI Summary
Managing and retrieving high-dimensional vector data poses significant challenges, particularly as traditional databases fail to meet performance requirements and the need for tight integration with large language models (LLMs) intensifies. Method: This paper systematically surveys four major approximate nearest neighbor search (ANNS) paradigms—hashing, tree-based indexing, graph-based methods (e.g., HNSW), and quantization (PQ/SQ)—and integrates hybrid optimization strategies. Contribution/Results: It introduces, for the first time, a “Four-Dimensional Methodology” framework tailored for industrial deployment of vector databases, analyzing trade-offs among accuracy, latency, memory footprint, and scalability. The work constructs a structured knowledge graph covering 200+ ANNS algorithms and proposes a novel paradigm for deep synergy between vector databases and LLMs. Collectively, these contributions provide both theoretical foundations and practical guidelines for system selection, architectural design, and development of AI-native database systems.
📝 Abstract
A vector database is used to store high-dimensional data that cannot be characterized by traditional DBMS. Although there are not many articles describing existing or introducing new vector database architectures, the approximate nearest neighbor search problem behind vector databases has been studied for a long time, and considerable related algorithmic articles can be found in the literature. This article attempts to comprehensively review relevant algorithms to provide a general understanding of this booming research area. The basis of our framework categorises these studies by the approach of solving ANNS problem, respectively hash-based, tree-based, graph-based and quantization-based approaches. Then we present an overview of existing challenges for vector databases. Lastly, we sketch how vector databases can be combined with large language models and provide new possibilities.
Problem

Research questions and friction points this paper is trying to address.

Review storage and retrieval techniques in vector databases
Compare advanced VDB solutions with strengths and limitations
Explore coupling VDBs with large language models
Innovation

Methods, ideas, or system contributions that make the work stand out.

Review of storage and retrieval techniques in VDBs
Comparison of advanced VDB solutions and applications
Coupling VDBs with large language models
🔎 Similar Papers
2024-01-302025 Conference on Artificial Intelligence x Multimedia (AIxMM)Citations: 38
2024-01-16arXiv.orgCitations: 76
Y
Yikun Han
Department of Statistics, University of Michigan, Ann Arbor, Michigan 48109, United States
C
Chunjiang Liu
Chengdu Library of the Chinese Academy of Sciences, Chengdu 610299, China
P
Pengfei Wang
Computer Network Information Center of the Chinese Academy of Sciences, Beijing 100190, China