# PQTable: Non-exhaustive Fast Search for Product-quantized Codes using Hash Tables

## TL;DR

The paper introduces PQTable, a fast, hash-table-based search method for product-quantized codes that outperforms linear scans and previous methods in speed and practicality, especially for large-scale, highly compressed data.

## Contribution

Proposes PQTable, a non-exhaustive, hash-based search method for product-quantized codes that avoids manual parameter tuning and training, enabling efficient large-scale retrieval.

## Key findings

- Achieves 10^2 to 10^5 times faster search than linear PQ scan.
- Handles highly compressed vectors with fast performance on a single CPU.
- Uses minimal memory (0.059 ms per query over 10^9 data points with 5.5 GB).

## Abstract

In this paper, we propose a product quantization table (PQTable); a fast search method for product-quantized codes via hash-tables. An identifier of each database vector is associated with the slot of a hash table by using its PQ-code as a key. For querying, an input vector is PQ-encoded and hashed, and the items associated with that code are then retrieved. The proposed PQTable produces the same results as a linear PQ scan, and is 10^2 to 10^5 times faster. Although state-of-the-art performance can be achieved by previous inverted-indexing-based approaches, such methods require manually-designed parameter setting and significant training; our PQTable is free of these limitations, and therefore offers a practical and effective solution for real-world problems. Specifically, when the vectors are highly compressed, our PQTable achieves one of the fastest search performances on a single CPU to date with significantly efficient memory usage (0.059 ms per query over 10^9 data points with just 5.5 GB memory consumption). Finally, we show that our proposed PQTable can naturally handle the codes of an optimized product quantization (OPQTable).