GateANN: I/O-Efficient Filtered Vector Search on SSDs

2026/03/23 by Nakyung Lee, Soobin Cho, Jiwoong Park +1 · 1 voice
Computer Science · #cs.DB #cs.OS

paper · pdf · doi:10.48550/arxiv.2603.21466

arxiv published 2026/03/23 · arxiv updated 2026/03/26

Abstract

We present GateANN, an I/O-efficient SSD-based graph ANNS system that supports filtered vector search on an unmodified graph index. Existing SSD-based systems either waste I/O by post-filtering, or require expensive filter-aware index rebuilds. GateANN avoids both by decoupling graph traversal from vector retrieval. Our key insight is that traversing a node requires only its neighbor list and an approximate distance, neither of which needs the full-precision vector on SSD. Based on this, GateANN introduces graph tunneling. It checks each node's filter predicate in memory before issuing I/O and routes through non-matching nodes entirely in memory, preserving graph connectivity without any SSD read for non-matching nodes. Our experimental results show that it reduces SSD reads by up to 10x and improves throughput by up to 7.6x.

Citations

• Scalable Disk-Based Approximate Nearest Neighbor Search with Page-Aligned Graph
• NaviX: A Native Vector Index Design for Graph DBMSs With Robust Predicate-Agnostic Search Performance
• Quake: Adaptive Indexing for Vector Search
• METIS: Fast Quality-Aware RAG Systems with Configuration Adaptation
• Results of the Big ANN: NeurIPS'23 competition
• CacheBlend: Fast Large Language Model Serving for RAG with Cached Knowledge Fusion
• ACORN: Performant and Predicate-Agnostic Search Over Vector Embeddings and Structured Data
• SPFresh: Incremental In-Place Update for Billion-Scale Vector Search
• Billion-scale similarity search with GPUs
• Efficient and robust approximate nearest neighbor search using Hierarchical Navigable Small World graphs

Discussions

• Nakyung Lee, Soobin Cho, Jiwoong Park, Gyuyeong Kim: GateANN: I/O-Efficient Filtered Vector Search on SSDs https://arxiv.org/abs/2603.21466 https://arxiv.org/pdf/2603.21466 https://arxiv.org/html/2603 [bsky, 0 points, 0 comments]

Related

• PipeANN-Filter: An Efficient Filtered Vector Search System on SSD
• DiskANN++: Efficient Page-based Search over Isomorphic Mapped Graph Index using Query-sensitivity Entry Vertex
• GoVector: An I/O-Efficient Caching Strategy for High-Dimensional Vector Nearest Neighbor Search
• Scalable Disk-Based Approximate Nearest Neighbor Search with Page-Aligned Graph
• PilotANN: Memory-Bounded GPU Acceleration for Vector Search