EMA: Approximate Nearest Neighbor Search with General Attribute Filtering and Dynamic Updates

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Li, Mocheng, Lu, Baotong, Cheng, James, Ma, Chenhao
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910276266229760
author Li, Mocheng
Lu, Baotong
Cheng, James
Ma, Chenhao
author_facet Li, Mocheng
Lu, Baotong
Cheng, James
Ma, Chenhao
contents Filtering Approximate Nearest Neighbor (FANN) search is a critical and emerging task for strengthening the query capability of vector databases, supporting applications such as recommendation systems, retrieval-augmented generation (RAG), and agent memory. However, most existing methods are limited to range or label filtering, often incurring unacceptable index construction time and memory overhead. Predicate-agnostic approaches further struggle to handle a wide range of predicate selectivities effectively. In this paper, we propose EMA, a filtering ANN algorithm that supports multi-predicate queries over mixed numerical and categorical attributes, and efficient dynamic updates. EMA introduces Markers as compact summaries attached to graph edges, providing conservative predicate- and geometric-aware guidance with zero false negatives at the Marker level. During query processing, EMA performs Marker-augmented joint search with a bounded edge recovery mechanism, enabling efficient filtering while preserving graph navigability. Extensive experiments demonstrate that EMA achieves 1.68x--12.25x speedup over state-of-the-art general filtering ANN methods across diverse workloads.
format Preprint
id arxiv_https___arxiv_org_abs_2606_00734
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle EMA: Approximate Nearest Neighbor Search with General Attribute Filtering and Dynamic Updates
Li, Mocheng
Lu, Baotong
Cheng, James
Ma, Chenhao
Databases
Filtering Approximate Nearest Neighbor (FANN) search is a critical and emerging task for strengthening the query capability of vector databases, supporting applications such as recommendation systems, retrieval-augmented generation (RAG), and agent memory. However, most existing methods are limited to range or label filtering, often incurring unacceptable index construction time and memory overhead. Predicate-agnostic approaches further struggle to handle a wide range of predicate selectivities effectively. In this paper, we propose EMA, a filtering ANN algorithm that supports multi-predicate queries over mixed numerical and categorical attributes, and efficient dynamic updates. EMA introduces Markers as compact summaries attached to graph edges, providing conservative predicate- and geometric-aware guidance with zero false negatives at the Marker level. During query processing, EMA performs Marker-augmented joint search with a bounded edge recovery mechanism, enabling efficient filtering while preserving graph navigability. Extensive experiments demonstrate that EMA achieves 1.68x--12.25x speedup over state-of-the-art general filtering ANN methods across diverse workloads.
title EMA: Approximate Nearest Neighbor Search with General Attribute Filtering and Dynamic Updates
topic Databases
url https://arxiv.org/abs/2606.00734