Improved Residual Vector Quantization for High-dimensional Approximate Nearest Neighbor Search
read the original abstract
Quantization methods have been introduced to perform large scale approximate nearest search tasks. Residual Vector Quantization (RVQ) is one of the effective quantization methods. RVQ uses a multi-stage codebook learning scheme to lower the quantization error stage by stage. However, there are two major limitations for RVQ when applied to on high-dimensional approximate nearest neighbor search: 1. The performance gain diminishes quickly with added stages. 2. Encoding a vector with RVQ is actually NP-hard. In this paper, we propose an improved residual vector quantization (IRVQ) method, our IRVQ learns codebook with a hybrid method of subspace clustering and warm-started k-means on each stage to prevent performance gain from dropping, and uses a multi-path encoding scheme to encode a vector with lower distortion. Experimental results on the benchmark datasets show that our method gives substantially improves RVQ and delivers better performance compared to the state-of-the-art.
This paper has not been read by Pith yet.
Forward citations
Cited by 4 Pith papers
-
HERMES: A Multi-Granularity Labeling Substrate for Pre-training Data Mixtures
HERMES provides a reusable hierarchical labeling substrate for pre-training data that reveals granularity-specific effects in data mixing rules during model training.
-
ASH: Asymmetric Scalar Hashing With Learned Dimensionality Reduction for High-Fidelity Vector Quantization
ASH achieves state-of-the-art ANN recall and speed across compression levels by learning an orthonormal projection for dimensionality reduction followed by scalar quantization in an asymmetric encoder-decoder setup.
-
ShopX: A Foundation Model for Intent-to-Item Fulfillment in Agentic Shopping
ShopX is a single foundation model combining intent understanding, planning, and SID-native item fulfillment for agentic shopping, with claimed improvements over tool-mediated systems on Taobao logs.
-
The Faiss library
Faiss is a library offering indexing methods and primitives for efficient vector similarity search, a core need in vector databases for AI applications.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.