Nearest neighbor search with compact codes: A decoder perspective

TL;DR

This paper reinterprets existing vector compression methods for nearest neighbor search as auto-encoders and introduces improved decoders that enhance reconstruction quality and retrieval performance on large datasets.

Contribution

It proposes backward-compatible decoders for binary hashing and product quantization, leading to better vector reconstruction and search accuracy.

Findings

Significant improvement over existing methods on benchmarks

Enhanced vector reconstruction quality

Better retrieval performance in large-scale datasets

Abstract

Modern approaches for fast retrieval of similar vectors on billion-scaled datasets rely on compressed-domain approaches such as binary sketches or product quantization. These methods minimize a certain loss, typically the mean squared error or other objective functions tailored to the retrieval problem. In this paper, we re-interpret popular methods such as binary hashing or product quantizers as auto-encoders, and point out that they implicitly make suboptimal assumptions on the form of the decoder. We design backward-compatible decoders that improve the reconstruction of the vectors from the same codes, which translates to a better performance in nearest neighbor search. Our method significantly improves over binary hashing methods or product quantization on popular benchmarks.