How Should We Evaluate Data Deletion in Graph-Based ANN Indexes?

2025-12-05

AI Summary

Existing graph-based approximate nearest neighbor search (ANNS) indices lack systematic evaluation of data deletion, particularly under realistic dynamic workloads. Method: This paper establishes a comprehensive evaluation framework tailored to practical dynamic scenarios and formally categorizes graph-based ANNS deletion methods into three distinct classes for the first time. It further proposes Deletion Control—a mechanism that dynamically selects deletion strategies via mathematical modeling and benchmark-driven optimization to adaptively balance accuracy and efficiency. Contribution/Results: Evaluated on HNSW, Deletion Control significantly improves deletion throughput and query stability while preserving retrieval accuracy. It enhances index maintainability and practicality in high-frequency update settings, enabling robust operation under continuous insertions and deletions without compromising search quality.

Technology Category

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

Application Category

• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Semantics and Knowledge: Scalable techniques for the creation, curation, publication, maintenance, and consumption of large, Web-based, structured, reusable, knowledge graphs and ontologies

Abstract

Approximate Nearest Neighbor Search (ANNS) has recently gained significant attention due to its many applications, such as Retrieval-Augmented Generation. Such applications require ANNS algorithms that support dynamic data, so the ANNS problem on dynamic data has attracted considerable interest. However, a comprehensive evaluation methodology for data deletion in ANNS has yet to be established. This study proposes an experimental framework and comprehensive evaluation metrics to assess the efficiency of data deletion for ANNS indexes under practical use cases. Specifically, we categorize data deletion methods in graph-based ANNS into three approaches and formalize them mathematically. The performance is assessed in terms of accuracy, query speed, and other relevant metrics. Finally, we apply the proposed evaluation framework to Hierarchical Navigable Small World, one of the state-of-the-art ANNS methods, to analyze the effects of data deletion, and propose Deletion Control, a method which dynamically selects the appropriate deletion method under a required search accuracy.

Problem

• Evaluates data deletion efficiency in graph-based ANN indexes
• Proposes framework to assess deletion methods' accuracy and speed
• Analyzes deletion effects on Hierarchical Navigable Small World indexes

Innovation

• Proposes evaluation framework for data deletion
• Categorizes deletion methods in graph-based ANNS
• Introduces dynamic deletion control method