发表机构
OceanBase, Ant Group; LIPADE, Université Paris Cité（蚂蚁集团; 巴黎西岱大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文提出联合建模语义相似度与时间新鲜度的 TANGO 方法，通过 Chronos 框架与分层图索引实现时间衰减向量搜索，在查询吞吐量、索引构建速度等方面优于现有方案，且鲁棒实用。
AI 中文摘要
向量搜索通常在固定评分函数下通过语义相似度衡量相关性。然而，在越来越多的应用中，相关性可能随时间演变，使得时间新鲜度成为语义相似度之外的补充信号。本文将时间衰减向量搜索（TDVS）形式化，将连续时间衰减纳入搜索目标，使相关性由语义相似度与时间新鲜度共同决定。我们设计了 Score-Preserving Temporal Reduction（STR，保评分时间约简），使现有的最大内积搜索索引可直接支持 TDVS。我们进一步提出 Chronos，一种原生 TDVS 框架，其推导了精确的度量公式，并引入查询正交时间提升（Query-Orthogonal TimeLift）以控制数据间几何结构，同时保留所有查询-数据评分与排序。基于 Chronos，我们提出 TANGO，一种分层图索引，采用层特定的 TimeLift 几何结构，在基础层保留时间局部性，在上层强化长范围语义连通性。TANGO 使用精确的 TDVS 评分遍历层次结构，缓存时间因子以减少计算，并支持高效的在线插入。大量实验表明，TANGO 的查询吞吐量比最先进的基于图的竞争对手高可达 3.5 倍，索引构建速度快 4.05 倍；在各类时间设置下，TANGO 均保持对所有竞争对手的优势，且支持高效在线插入，展现出其鲁棒性与实用性。
英文摘要
Vector search typically measures relevance through semantic similarity under a fixed scoring function. However, in a growing range of applications, relevance may evolve over time, making temporal freshness an additional signal beyond semantic similarity. In this paper, we formalize time-decayed vector search (TDVS), which incorporates continuous temporal decay into the search objective so that relevance is jointly determined by semantic similarity and temporal freshness. We design Score-Preserving Temporal Reduction (STR) that enables existing Maximum Inner Product Search indexes to directly support TDVS. We further present Chronos, a TDVS-native framework that derives an exact metric formulation and introduces Query-Orthogonal TimeLift to control data--data geometry while preserving all query--data scores and rankings. Building on Chronos, we propose TANGO, a hierarchical graph index that adopts layer-specific TimeLift geometries to preserve temporal locality at the base layer while strengthening long-range semantic connectivity in upper layers. TANGO traverses the hierarchy using the exact TDVS score, caches temporal factors to reduce computation, and supports efficient online insertion. Extensive experiments show that TANGO achieves up to 3.5$\times$ higher query throughput and 4.05$\times$ faster index construction than state-of-the-art graph-based competitors. TANGO also maintains its advantage over all competitors across diverse temporal settings and enables efficient online insertion, demonstrating its robustness and practicality.
