Graph-based Nearest Neighbors with Dynamic Updates via Random Walk-Based Analysis

ICLR 2026 Conference Submission20621 Authors

Keywords: nearest neighbor search, graph, random walk

TL;DR: We propose a random-walk based analytical framework for HNSW, and use it to design a deterministic deletion algorithm with good recall, throughput and memory utilization.

Abstract: Approximate nearest neighbor search (ANN) is a common way to retrieve relevant search results, especially now in the context of large language models and retrieval augmented generation. One of the most widely used algorithms for ANN is based on constructing a multi-layer graph over the dataset, called the Hierarchical Navigable Small World (HNSW). While this algorithm supports insertion of new data, it does not support deletion of existing data. Moreover, deletion algorithms described by prior work come at the cost of increased query latency, decreased recall, or prolonged deletion time. In this paper, we propose a new theoretical framework for graph-based ANN based on random walks. We then utilize this framework to analyze a randomized deletion approach that preserves hitting time statistics compared to the graph before deleting the point. We then turn this theoretical framework into a \emph{deterministic} deletion algorithm, and show that it provides better tradeoff between query latency, recall, deletion time, and memory usage through an extensive collection of experiments.

Primary Area: optimization

Submission Number: 20621