Problem
Research questions and friction points this paper is trying to address.
Dynamic Vector Datasets
Time-Aware Nearest Neighbor Search
Arbitrary Time Intervals
A Versioned Unified Graph Index for Dynamic Timestamp-Aware Nearest Neighbor Search
🤖 AI Summary
本文提出TiGER算法，通过构建统一版本图索引解决动态数据集上时间感知最近邻搜索问题，提高查询效率。
📝 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 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.
Innovation
Methods, ideas, or system contributions that make the work stand out.
time-aware nearest neighbor search
dynamic vector datasets
unified graph index
versioned connectivity
real-time recommendation systems
🔎 Similar Papers
