PulseExploreJournal ClubDebatesTrendingResearchersJournals
Instagram
HomeExploreJournal ClubTrending
Synapse
⌘+K
Synapse
March 21, 2026Proceedings of the VLDB Endowment2 citations

A Topology-Aware Localized Update Strategy for Graph-Based ANN Index

View Full Paper
SYSong YuSLShengyuan LinSGShufeng Gong

Key Points

  • The goal is to enhance the update process in graph-based approximate nearest neighbor search systems by addressing limitations with small-batch updates.
  • Proposed a topology-aware localized update strategy for small-batch updates.
  • Developed a lightweight graph topology to quickly identify affected nodes.
  • Implemented a localized update mechanism to limit changes to specific index pages.
  • Designed a similarity-aware connection method for linking affected nodes to similar neighbors.
  • Achieved 2.39–5.96× higher update throughput compared to the state-of-the-art system FreshDiskANN.
  • Maintained high search efficiency and accuracy during the updates.

Abstract

Graph-based indices are widely used for approximate nearest neighbor search (ANNS). Under dynamic workloads, existing ANNS systems amortize update overhead with large batches, but large batches degrade index quality. We identify two key limitations in existing systems when handling small-batch updates. First, they still scan the entire index to repair the affected graph topology and rebuild the index, causing heavy I/O. Second, their naive repair introduces many edges, repeatedly triggering costly neighbor pruning with expensive distance computations. To address these issues, we propose a topology-aware localized update strategy that exploits the locality of small-batch updates to reduce unnecessary I/O and computation. Specifically, we introduce a lightweight graph topology that quickly identifies affected nodes without full index scans, and a localized update mechanism that restricts modifications to the pages containing these nodes. Moreover, we design a similarity-aware localized connection method that links each affected node to a small set of highly similar neighbors, avoiding redundant edges and costly pruning. Extensive experiments show that our update strategy achieves 2.39–5.96× higher update throughput than the state-of-the-art graph-based streaming ANNS system FreshDiskANN while maintaining high search efficiency and accuracy.

Ask AI
Helpful
Bookmark
Share
View Full Paper

Cite This Study

Yu et al. (2025) studied this question.

synapsesocial.com/papers/69be38356e48c4981c678769https://doi.org/10.14778/3778092.3778108
Ask AI
Helpful
Bookmark
Share
View Full Paper