用统一图结构实现动态向量数据的高效时序近邻搜索。
A Versioned Unified Graph Index for Dynamic Timestamp-Aware Nearest Neighbor Search
- 构建带版本连接的统一图，支持任意时间区间的直接查询。
- 查询速度比基线方法快5倍，且精度不下降。
- 适合实时推荐、日志分析等需要时序相似性搜索的场景。
我们提出TiGER（Time-Integrated Graph for Efficient Retrieval），一种在动态向量数据集上实现快速时序感知近似最近邻搜索的新方法，可灵活处理任意时间范围。该方法通过基于集成版本化连接的索引结构，构建并维护所有向量的统一图，使任意时间区间可直接在统一图上查询，无需遍历无效向量或进行事后过滤与合并，也无需为每个可能的时间组合建立独立子图。实证评估表明，本方法在不牺牲准确性的前提下，查询吞吐量（QPS）相比基于过滤或分时段子图的基线方法最高提升5倍。我们认为该方法将推动实时推荐系统、日志分析等场景中对演化数据的高效时序分析。
原文摘要 · Abstract (English)
We present TiGER (Time-Integrated Graph for Efficient Retrieval), a novel approach for performing fast time-aware approximate nearest neighbor searches on dynamic vector datasets with flexibility over any possible time range. Our proposed algorithm builds and maintains a unified graph for all vectors by leveraging an index structure based on integrated versioned connectivity, allowing arbitrary time intervals to be queried directly on the unified graph without having to traverse invalid vectors. This forgoes the need for post-search filtering or merging, or separate graphs for each possible composite range. Empirical evaluations show that our method attains up to a 5x improvement in queries per second (QPS) without compromising accuracy over baselines based on filtering or per-time-segment sub-graphs. We believe that this method will enable efficient temporal analysis across evolving datasets in real-time recommendation systems, log analysis, and any scenario requiring fast similarity search over dynamic, time-segmented data.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。