Scalable Disk-Based Approximate Nearest Neighbor Search with Page-Aligned Graph

2025-09-29

AI Summary

To address memory constraints, lengthy I/O paths, storage-granularity mismatches, and excessive indexing overhead in large-scale vector search—particularly for SSD-based approximate nearest neighbor search (ANNS)—this paper proposes PageANN, the first SSD-oriented, page-aligned graph indexing framework. Its core innovation lies in a page-node graph structure that strictly aligns logical graph nodes with SSD physical pages, coupled with clustering-aware storage, topology compression, representative-vector merging, and cooperative memory management to achieve I/O-efficient data layout and lightweight indexing. Evaluated across multiple datasets and varying memory budgets, PageANN achieves 1.85×–10.83× higher throughput and reduces latency by 51.7%–91.9% compared to state-of-the-art methods, while maintaining high recall. This significantly enhances scalability and efficiency of disk-native vector retrieval.

Technology Category

• Search and Optimization: Distributed Search
• Machine Learning: Graph-based Machine Learning
• Computer Vision: Image and Video Retrieval

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
• Social Networks and Social Media: Social mining and social search on the Web

Abstract

Approximate Nearest Neighbor Search (ANNS), as the core of vector databases (VectorDBs), has become widely used in modern AI and ML systems, powering applications from information retrieval to bio-informatics. While graph-based ANNS methods achieve high query efficiency, their scalability is constrained by the available host memory. Recent disk-based ANNS approaches mitigate memory usage by offloading data to Solid-State Drives (SSDs). However, they still suffer from issues such as long I/O traversal path, misalignment with storage I/O granularity, and high in-memory indexing overhead, leading to significant I/O latency and ultimately limiting scalability for large-scale vector search. In this paper, we propose PageANN, a disk-based approximate nearest neighbor search (ANNS) framework designed for high performance and scalability. PageANN introduces a page-node graph structure that aligns logical graph nodes with physical SSD pages, thereby shortening I/O traversal paths and reducing I/O operations. Specifically, similar vectors are clustered into page nodes, and a co-designed disk data layout leverages this structure with a merging technique to store only representative vectors and topology information, avoiding unnecessary reads. To further improve efficiency, we design a memory management strategy that combines lightweight indexing with coordinated memory-disk data allocation, maximizing host memory utilization while minimizing query latency and storage overhead. Experimental results show that PageANN significantly outperforms state-of-the-art (SOTA) disk-based ANNS methods, achieving 1.85x-10.83x higher throughput and 51.7%-91.9% lower latency across different datasets and memory budgets, while maintaining comparable high recall accuracy.

Problem

• Addresses scalability limitations of graph-based ANNS methods
• Reduces I/O latency by aligning graph nodes with SSD pages
• Minimizes memory indexing overhead through optimized data layout

Innovation

• Page-node graph aligns nodes with SSD pages
• Clustering vectors into page nodes reduces I/O
• Lightweight indexing with coordinated memory-disk allocation