发表机构
Khalifa University（哈利法大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
提出无索引动态边检索方法ETAR，通过保留查询高幅值坐标、校正低幅值尾并重新排序候选，在保持简单更新的同时实现高召回率与快速查询，适用于静态、移动及流工作负载场景。
AI 中文摘要
动态最大内积搜索（MIPS）返回与查询向量点积最大的K个存储向量，同时允许数据集通过插入、替换和删除操作进行更新。对于边检索而言，挑战在于在实现高召回率和快速查询的同时，避免更新操作成本过高。全向量扫描使更新操作简单，但会将每个查询与所有存储向量进行比较；而索引方法虽降低了查询成本，却需在更新期间维护额外结构。我们提出ETAR，一种无索引方法，在保持更新操作简单的同时减少查询工作量。ETAR保留查询向量中平方值最大的坐标，直至这些坐标覆盖其总平方幅值的大部分，将其余部分视为低幅值尾；它使用紧凑的低精度表示从保留的坐标估计相似度，对被跳过的坐标进行校正，并使用全精度向量对固定数量的候选进行重新排序。在9个静态数据集上进行的5次运行中，ETAR的平均Recall@10（精确前10结果的恢复比例）为99.2%，在代表性设置下的运行速度比精确扫描快4倍以上；该加速效果还延伸至基于ARM的移动设备，在4种合成分布下，ETAR的速度最高可达6.9倍。在5个流工作负载下，ETAR在每个测量点均保持100%的Recall@10，且无需重建索引。总体而言，ETAR为动态MIPS提供了一种实用的中间方案，在降低查询成本的同时，保留了简单的无索引更新操作。代码可在该https URL获取。
英文摘要
Dynamic maximum inner-product search (MIPS) returns the $K$ stored vectors with the largest dot products with a query while allowing the dataset to change through insertions, replacements, and deletions. For edge retrieval, the challenge is to achieve high recall and fast queries without making updates expensive. Full-vector scanning keeps updates simple but compares each query with every stored vector, while indexed methods reduce query cost at the expense of maintaining additional structures during updates. We propose ETAR, an index-free method that reduces query work while preserving simple updates. ETAR keeps the query coordinates with the largest squared values until they cover most of its total squared magnitude and treats the rest as a low-magnitude tail. It estimates similarity from the retained coordinates using a compact lower-precision representation, corrects for skipped coordinates, and reranks a fixed number of candidates using full-precision vectors. Across five runs on nine static datasets, ETAR averages 99.2% Recall@10, the fraction of exact top-10 results recovered, while running over 4$\times$ faster than exact scanning at a representative setting. This speedup also extends to an ARM-based mobile device, where ETAR is up to 6.9$\times$ faster across four synthetic distributions. Under five streaming workloads, it maintains 100% Recall@10 at every measured point without index rebuilds. Overall, ETAR offers a practical middle ground for dynamic MIPS by reducing query cost while retaining simple, index-free updates. Code is available at https://github.com/arasyi/etar-mips.
CommentsAccepted for presentation at the 2026 IEEE 12th World Forum on Internet of Things (WF-IoT)
