TiGER：面向动态时间感知最近邻搜索的统一版本化图索引
原标题：A Versioned Unified Graph Index for Dynamic Timestamp-Aware Nearest Neighbor Search
AI 摘要
arXiv 论文提出 TiGER（Time-Integrated Graph for Efficient Retrieval），一种用于动态向量数据集的时间感知近似最近邻搜索方法。TiGER 通过构建和维护统一图索引，利用版本化连通性，支持任意时间范围的直接查询，无需后过滤或合并。实验表明，在保持准确率的同时，查询吞吐量（QPS）相比基线最高提升 5 倍，适用于实时推荐系统和日志分析等场景。
正文节选
A Versioned Unified Graph Index for Dynamic Timestamp-Aware Nearest Neighbor Search Abstract 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 inte