Tiered Cache-HNSW: Using Hierarchical Caching System in HNSW
Authors:
- 29 March 2025
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-4
Abstract
With the progress in generative AI technology, systems such as RAG (Retrieval-Augmented Generation) are increasingly used. In these systems, graph-based Approximate Nearest Neighbor Search (ANNS) is commonly used for background information retrieval. However, as the size of the dataset increases, the search speed becomes significantly slower. In this paper, we propose Tiered Cache-HNSW (TC-HNSW) that caches pre-categorized datasets in layers. TC- HNSW prioritizes caching frequently accessed nodes into faster storage based on the number of accesses and their category, allowing faster searches. This paper describes TC- HNSW system design, caching strategy, and the efficiency of categorization-based caching. Our preliminary evaluation shows that categorization-based caching improves performance, achieving search speeds four times faster than traditional methods when search topics are specified.Keywords
This publication has 3 references indexed in Scilit:
- A comprehensive survey and experimental comparison of graph-based approximate nearest neighbor searchProceedings of the VLDB Endowment, 2021
- Efficient and Robust Approximate Nearest Neighbor Search Using Hierarchical Navigable Small World GraphsIEEE Transactions on Pattern Analysis and Machine Intelligence, 2018
- Product Quantization for Nearest Neighbor SearchIEEE Transactions on Pattern Analysis and Machine Intelligence, 2010