On-disk graph-based indexes are widely used in approximate nearest neighbor (ANN) search systems for large-scale, high-dimensional vectors. However, traditional coupled storage methods, which store vectors within the index, are inefficient for index updates. Coupled storage incurs excessive redundant vector reads and writes when updating the graph topology, leading to significant invalid I/O. To address this issue, we propose a decoupled storage architecture. While a decoupled architecture reduces query performance. To overcome this limitation, we design two tailored strategies: (i) a three-stage query mechanism that leverages multiple PQ compressed vectors to filter invalid I/O and computations, and (ii) an incremental page-level topological reordering strategy that incrementally inserts new nodes into pages containing their most similar neighbors to mitigate read amplification. Together, these techniques substantially reduce both I/O and computational overhead during ANN search. Experimental results show that the decoupled architecture improves update speed by 10.05x for insertions and 6.89x for deletions, while the three-stage query and incremental reordering enhance query efficiency by 2.66x compared to the traditional coupled architecture.

翻译：基于磁盘的图结构索引在大规模高维向量的近似最近邻（ANN）搜索系统中得到广泛应用。然而，传统耦合存储方法将向量存储在索引内部，导致索引更新效率低下。耦合存储在更新图拓扑时会产生大量冗余的向量读写，引发显著的无用I/O。为解决此问题，我们提出一种解耦存储架构。尽管解耦架构会降低查询性能，为克服这一局限，我们设计了两种定制策略：（i）利用多个乘积量化压缩向量的三阶段查询机制，以过滤无效I/O和计算；（ii）增量式页面级拓扑重排序策略，将新节点逐步插入至包含其最相似邻居的页面中，以缓解读放大效应。这些技术共同显著降低了ANN搜索过程中的I/O与计算开销。实验结果表明，解耦架构将插入和删除操作的更新速度分别提升10.05倍和6.89倍，而三阶段查询与增量重排序策略使查询效率较传统耦合架构提升2.66倍。