# SPFresh: Incremental In-Place Update for Billion-Scale Vector Search

arXiv: https://arxiv.org/abs/2410.14452 · HTML: https://mlsanity.com/paper/2410.14452/

## Key facts

- Cited by 28 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 18 Oct 2024.

## Built on by (most cited first, 28 of 28)

- [RAGO: Systematic Performance Optimization for Retrieval-Augmented Generation Serving](https://mlsanity.com/paper/2503.14649/) (2025)
- [Quake: Adaptive Indexing for Vector Search](https://mlsanity.com/paper/2506.03437/) (2025)
- [Incremental IVF Index Maintenance for Streaming Vector Search](https://mlsanity.com/paper/2411.00970/) (2024)
- [MicroNN: An On-device Disk-resident Updatable Vector Database](https://mlsanity.com/paper/2504.05573/) (2025)
- [Pancake: Hierarchical Memory System for Multi-Agent LLM Serving](https://mlsanity.com/paper/2602.21477/) (2026)
- [LSM-VEC: A Large-Scale Disk-Based System for Dynamic Vector Search](https://mlsanity.com/paper/2505.17152/) (2025)
- [Cracking Vector Search Indexes](https://mlsanity.com/paper/2503.01823/) (2025)
- [Drift-Adapter: A Practical Approach to Near Zero-Downtime Embedding Model Upgrades in Vector Databases](https://mlsanity.com/paper/2509.23471/) (2025)
- [Cloud-Native Vector Search: A Comprehensive Performance Analysis](https://mlsanity.com/paper/2511.14748/) (2025)
- [HAKES: Scalable Vector Database for Embedding Search Service](https://mlsanity.com/paper/2505.12524/) (2025)
- [Scalable Disk-Based Approximate Nearest Neighbor Search with Page-Aligned Graph](https://mlsanity.com/paper/2509.25487/) (2025)
- [A Super Fast K-means for Indexing Vector Embeddings](https://mlsanity.com/paper/2603.20009/) (2026)
- [How Should We Evaluate Data Deletion in Graph-Based ANN Indexes?](https://mlsanity.com/paper/2512.06200/) (2025)
- [GPU-Accelerated Algorithms for Graph Vector Search: Taxonomy, Empirical Study, and Research Directions](https://mlsanity.com/paper/2602.16719/) (2026)
- [Passing the Baton: High Throughput Distributed Disk-Based Vector Search with BatANN](https://mlsanity.com/paper/2512.09331/) (2025)
- [Graph-based Nearest Neighbors with Dynamic Updates via Random Walks](https://mlsanity.com/paper/2512.18060/) (2025)
- [Efficient K-generalizable Learned Search](https://mlsanity.com/paper/2603.06159/) (2026)
- [FGIM: a Fast Graph-based Indexes Merging Framework for Approximate Nearest Neighbor Search](https://mlsanity.com/paper/2603.21710/) (2026)
- [IVF-TQ: Calibration-Free Streaming Vector Search via a Codebook-Free Residual Layer](https://mlsanity.com/paper/2605.17415/) (2026)
- [NasZip: Software and Hardware Co-Design to Accelerate Approximate Nearest Neighbor Search with DIMM-Based Near-Data Processing](https://mlsanity.com/paper/2605.21952/) (2026)
- [Digitizing Coaching Intelligence: An Agentic Framework for Holistic Athlete Profiling using VLM and RAG](https://mlsanity.com/paper/2606.28570/) (2026)
- [ANNLib: A Development Framework for Efficient Approximate Nearest Neighbor Search](https://mlsanity.com/paper/2607.17582/) (2026)
- [MERIT: Efficient In-Place Deletion for Dynamic Graph-Based Approximate Nearest Neighbor Indexes](https://mlsanity.com/paper/2607.29173/) (2026)
- [SafeQL: Search-based Refinement for Safe and Efficient LLM-based Text-to-SQL](https://mlsanity.com/paper/2608.09260/) (2026)
- [Stop Indexing at Full Precision: Revisiting Clustering for Vector Embeddings](https://mlsanity.com/paper/2608.14648/) (2026)
- [A Functional Pilot for Certified Freshness-Aware Semantic--Spatial Range Retrieval](https://mlsanity.com/paper/2609.19855/) (2026)
- [Hybrid GPU-CPU Retrieval for Personalized Search at Ultra-Large Scale](https://mlsanity.com/paper/2609.21281/) (2026)
- [Exploiting Residual Reachability for Cross-Model Migration of Graph-Based Indexes in Approximate Nearest Neighbor Search](https://mlsanity.com/paper/2609.23036/) (2026)

## Abstract (arXiv)

Approximate Nearest Neighbor Search (ANNS) is now widely used in various applications, ranging from information retrieval, question answering, and recommendation, to search for similar high-dimensional vectors. As the amount of vector data grows continuously, it becomes important to support updates to vector index, the enabling technique that allows for efficient and accurate ANNS on vectors. Because of the curse of high dimensionality, it is often costly to identify the right neighbors of a single new vector, a necessary process for index update. To amortize update costs, existing systems maintain a secondary index to accumulate updates, which are merged by the main index by global rebuilding the entire index periodically. However, this approach has high fluctuations of search latency and accuracy, not even to mention that it requires substantial resources and is extremely time-consuming for rebuilds. We introduce SPFresh, a system that supports in-place vector updates. At the heart of SPFresh is LIRE, a lightweight incremental rebalancing protocol to split vector partitions and reassign vectors in the nearby partitions to adapt to data distribution shift. LIRE achieves low-overhead vector updates by only reassigning vectors at the boundary between partitions, where in a high-quality vector index the amount of such vectors are deemed small. With LIRE, SPFresh provides superior query latency and accuracy to solutions based on global rebuild, with only 1% of DRAM and less than 10% cores needed at the peak compared to the state-of-the-art, in a billion scale vector index with 1% of daily vector update rate.