RAE: A Neural Network Dimensionality Reduction Method for Nearest Neighbors Preservation in Vector Search

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Zhang, Han, Zhao, Dongfang
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866914067450429440
author Zhang, Han
Zhao, Dongfang
author_facet Zhang, Han
Zhao, Dongfang
contents While high-dimensional embedding vectors are being increasingly employed in various tasks like Retrieval-Augmented Generation and Recommendation Systems, popular dimensionality reduction (DR) methods such as PCA and UMAP have rarely been adopted for accelerating the retrieval process due to their inability of preserving the nearest neighbor (NN) relationship among vectors. Empowered by neural networks' optimization capability and the bounding effect of Rayleigh quotient, we propose a Regularized Auto-Encoder (RAE) for k-NN preserving dimensionality reduction. RAE constrains the network parameter variation through regularization terms, adjusting singular values to control embedding magnitude changes during reduction, thus preserving k-NN relationships. We provide a rigorous mathematical analysis demonstrating that regularization establishes an upper bound on the norm distortion rate of transformed vectors, thereby offering provable guarantees for k-NN preservation. With modest training overhead, RAE achieves superior k-NN recall compared to existing DR approaches while maintaining fast retrieval efficiency.
format Preprint
id arxiv_https___arxiv_org_abs_2509_25839
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle RAE: A Neural Network Dimensionality Reduction Method for Nearest Neighbors Preservation in Vector Search
Zhang, Han
Zhao, Dongfang
Information Retrieval
Artificial Intelligence
Databases
While high-dimensional embedding vectors are being increasingly employed in various tasks like Retrieval-Augmented Generation and Recommendation Systems, popular dimensionality reduction (DR) methods such as PCA and UMAP have rarely been adopted for accelerating the retrieval process due to their inability of preserving the nearest neighbor (NN) relationship among vectors. Empowered by neural networks' optimization capability and the bounding effect of Rayleigh quotient, we propose a Regularized Auto-Encoder (RAE) for k-NN preserving dimensionality reduction. RAE constrains the network parameter variation through regularization terms, adjusting singular values to control embedding magnitude changes during reduction, thus preserving k-NN relationships. We provide a rigorous mathematical analysis demonstrating that regularization establishes an upper bound on the norm distortion rate of transformed vectors, thereby offering provable guarantees for k-NN preservation. With modest training overhead, RAE achieves superior k-NN recall compared to existing DR approaches while maintaining fast retrieval efficiency.
title RAE: A Neural Network Dimensionality Reduction Method for Nearest Neighbors Preservation in Vector Search
topic Information Retrieval
Artificial Intelligence
Databases
url https://arxiv.org/abs/2509.25839