Efficient and Effective In-place Graph-based Vector Index Updates

• URL: http://arxiv.org/abs/2607.15576v1
• Date: Fri, 17 Jul 2026 02:40:08 GMT
• Title: Efficient and Effective In-place Graph-based Vector Index Updates
• Abstract summary: We introduce a vector-level update mechanism and architect Yi with three core components.<n>Yi achieves 1.75x higher update throughput and 1.8x higher concurrent search throughput than the state-of-the-art systems on the 800M dataset.
• Score: 27.624578663931604
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: In the era of Large Language Models (LLMs), efficient vector updates are critical for capturing real-time information from rapidly evolving data. However, it is not trivial to process frequent vector insert and delete updates and maintain a high recall of the search results simultaneously. Specifically, the cluster-based vector indexing methods have high update throughput but low search result quality. Existing out-of-place graph-based vector indexing update approaches suffer from poor update throughput due to the need to periodically merge update batches into the underlying graph index. Building a vector data system that supports efficient and effective in-place updates is inherently challenging. In this work, we propose Yi to achieve it. In particular, Yi supports in-place graph-based vector indexing updates with consistently high update throughput and good search result quality. The key idea of Yi is decomposition facilitates consolidation. In particular, we introduce a vector-level update mechanism and architect Yi with three core components: (i) a tasklet-based execution engine, (ii) an asynchronous buffer manager, and (iii) a vector file system. Experimental results demonstrate that Yi achieves 1.75x higher update throughput and 1.8x higher concurrent search throughput than the state-of-the-art systems on the 800M dataset, while using only 73% of the peak memory and fewer CPU cores.

Related papers

• No More K-means: Single-Stage Sparse Coding for Efficient Multi-Vector Retrieval [51.43543998583709]
  Single-stage Sparse Retrieval (SSR) is a paradigm shift that replaces expensive clustering with efficient sparse coding.<n>It reduces indexing time by 15x compared to ColBERTv2, halves retrieval latency, and simultaneously improves retrieval performance.
  arXiv  Detail & Related papers  (2026-05-28T15:53:34Z)
• An Embarrassingly Simple Graph Heuristic Reveals Shortcut-Solvable Benchmarks for Sequential Recommendation [50.09718257952108]
  Sequentialsolv has increasingly shifted toward generative recommenders that combine sequential patterns with semantic item information.<n>These methods are often evaluated on a small set of widely used benchmarks, raising a key question: do these benchmarks actually require the advanced modeling capabilities that modern generative recommenders claim to provide?<n>We conduct a benchmark audit with an intentionally simple graph. Starting from only the last one or two items, it retrieves candidates from a few-hop item-transition graph and ranks them by item-feature similarity.
  arXiv  Detail & Related papers  (2026-05-08T02:00:11Z)
• ITS3D: Inference-Time Scaling for Text-Guided 3D Diffusion Models [88.04431808574581]
  ITS3D is a framework that formulates the task as an optimization problem to identify the most effective Gaussian noise input.<n>We introduce three techniques for improved stability, efficiency, and exploration capability.<n>Experiments demonstrate that ITS3D enhances text-to-3D generation quality.
  arXiv  Detail & Related papers  (2025-11-27T13:46:16Z)
• TeaRAG: A Token-Efficient Agentic Retrieval-Augmented Generation Framework [62.66056331998838]
  TeaRAG is a token-efficient agentic RAG framework capable of compressing both retrieval content and reasoning steps.<n>Our reward function evaluates the knowledge sufficiency by a knowledge matching mechanism, while penalizing excessive reasoning steps.
  arXiv  Detail & Related papers  (2025-11-07T16:08:34Z)
• DGAI: Decoupled On-Disk Graph-Based ANN Index for Efficient Updates and Queries [14.147837695174722]
  On-disk graph-based indexes are widely used in approximate nearest neighbor (ANN) search systems for large-scale, high-dimensional vectors.<n>Traditional coupled storage methods, which store vectors within the index, are inefficient for index updates.<n>We propose a decoupled storage architecture, while a decoupled architecture reduces query performance.
  arXiv  Detail & Related papers  (2025-10-29T11:20:10Z)
• CleANN: Efficient Full Dynamism in Graph-based Approximate Nearest Neighbor Search [6.319134122855477]
  Approximate nearest neighbor search (ANNS) has become a quintessential algorithmic problem for various other foundational data tasks for AI workloads.<n>Most existing graph-based indexes are designed for the static scenario, where there are no updates to the data after the index is constructed.<n>CleANN is the first concurrent ANNS index to achieve such efficiency while maintaining quality under full dynamism.
  arXiv  Detail & Related papers  (2025-07-26T05:27:32Z)
• HAKES: Scalable Vector Database for Embedding Search Service [16.034584281180006]
  We build a vector database that achieves high throughput and high recall under concurrent read-write workloads.<n>Our index outperforms index baselines in the high recall region and under concurrent read-write workloads.<n>namesys is scalable and achieves up to $16times$ higher throughputs than the baselines.
  arXiv  Detail & Related papers  (2025-05-18T19:26:29Z)
• In-Place Updates of a Graph Index for Streaming Approximate Nearest Neighbor Search [12.092920351505036]
  IP-DiskANN is first algorithm to avoid batch consolidation by efficiently processing each insertion and deletion in-place.<n>It has stable recall over various lengthy update patterns in both high-recall and low-recall regimes.
  arXiv  Detail & Related papers  (2025-02-19T15:41:08Z)
• SPFresh: Incremental In-Place Update for Billion-Scale Vector Search [19.245438083030006]
  We introduce SPFresh, a system that supports in-place vector updates. At the heart of SPFresh is LIRE, a lightweight incremental rebalancing protocol. With LIRE, SPFresh provides superior query latency and accuracy to solutions based on global rebuild.
  arXiv  Detail & Related papers  (2024-10-18T13:24:18Z)
• TimeGraphs: Graph-based Temporal Reasoning [64.18083371645956]
  TimeGraphs is a novel approach that characterizes dynamic interactions as a hierarchical temporal graph. Our approach models the interactions using a compact graph-based representation, enabling adaptive reasoning across diverse time scales. We evaluate TimeGraphs on multiple datasets with complex, dynamic agent interactions, including a football simulator, the Resistance game, and the MOMA human activity dataset.
  arXiv  Detail & Related papers  (2024-01-06T06:26:49Z)
• Efficient Few-Shot Object Detection via Knowledge Inheritance [62.36414544915032]
  Few-shot object detection (FSOD) aims at learning a generic detector that can adapt to unseen tasks with scarce training samples. We present an efficient pretrain-transfer framework (PTF) baseline with no computational increment. We also propose an adaptive length re-scaling (ALR) strategy to alleviate the vector length inconsistency between the predicted novel weights and the pretrained base weights.
  arXiv  Detail & Related papers  (2022-03-23T06:24:31Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.