Individualized non-uniform quantization for vector search

2025-09-22

AI Summary

Storing and retrieving high-dimensional embedding vectors incurs substantial memory overhead and computational cost. To address this, we propose Non-uniform Vector Quantization (NVQ), the first method that learns a customizable, lightweight nonlinear transformation for each index vector to enable personalized non-uniform quantization. Departing from conventional uniform quantization schemes, NVQ models local data distributions via compact, differentiable functions, achieving high-fidelity compression with minimal computational overhead. Extensive experiments on standard benchmarks demonstrate that NVQ consistently outperforms state-of-the-art methods—including PQ, OPQ, and AQ—at equivalent compression ratios, improving average Recall@10 by 3.2–7.8 percentage points while maintaining millisecond-scale query latency. Our core contributions are: (i) the first individualized non-uniform quantization framework tailored for approximate nearest neighbor (ANN) search; (ii) an efficient, learnable nonlinear transformation mechanism; and (iii) joint optimization of accuracy, efficiency, and compression ratio.

Technology Category

• Search and Optimization: Non-convex Optimization
• Data Mining & Knowledge Management: Data Compression
• Machine Learning: Learning on the Edge & Model Compression

Application Category

• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Graph Algorithms and Modeling for the Web: Graph embeddings and representation learning for Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Embedding vectors are widely used for representing unstructured data and searching through it for semantically similar items. However, the large size of these vectors, due to their high-dimensionality, creates problems for modern vector search techniques: retrieving large vectors from memory/storage is expensive and their footprint is costly. In this work, we present NVQ (non-uniform vector quantization), a new vector compression technique that is computationally and spatially efficient in the high-fidelity regime. The core in NVQ is to use novel parsimonious and computationally efficient nonlinearities for building non-uniform vector quantizers. Critically, these quantizers are emph{individually} learned for each indexed vector. Our experimental results show that NVQ exhibits improved accuracy compared to the state of the art with a minimal computational cost.

Problem

• Compressing high-dimensional embedding vectors for efficient storage
• Reducing memory retrieval costs in vector search techniques
• Improving accuracy of vector quantization with minimal computational overhead

Innovation

• Individualized non-uniform quantization per vector
• Parsimonious nonlinearities for efficient quantizers
• Minimal computational cost with improved accuracy