EMA: Approximate Nearest Neighbor Search with General Attribute Filtering and Dynamic Updates
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| 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 |