• Computer Science > Databases [Submitted on 17 Feb 2026] Title:PiPNN: Ultra-Scalable Graph-Based Nearest Neighbor Indexing View PDF HTML (experimental)Abstract:The fastest indexes for Approximate Nearest Neighbor Search today are also the slowest to build: graph-based methods like HNSW and Vamana achieve state-of-the-art query performance but have large construction times due to relying on random-access-heavy beam searches • We introduce PiPNN (Pick-in-Partitions Nearest Neighbors), an ultra-scalable graph construction algorithm that avoids this ``search bottleneck’’ that existing graph-based methods suffer from • PiPNN’s core innovation is HashPrune, a novel online pruning algorithm which dynamically maintains sparse collections of edges • HashPrune enables PiPNN to partition the dataset into overlapping sub-problems, efficiently perform bulk distance comparisons via dense matrix multiplication kernels, and stream a subset of the edges into HashPrune • HashPrune guarantees bounded memory during index construction which permits PiPNN to build higher quality indices without the use of extra intermediate memory • PiPNN builds state-of-the-art indexes up to 11

Article Summaries:

  • Computer Science > Databases [Submitted on 17 Feb 2026] Title:PiPNN: Ultra-Scalable Graph-Based Nearest Neighbor Indexing View PDF HTML (experimental)Abstract:The fastest indexes for Approximate Nearest Neighbor Search today are also the slowest to build: graph-based methods like HNSW and Vamana achieve state-of-the-art query performance but have large construction times due to relying on random-access-heavy beam searches. We introduce PiPNN (Pick-in-Partitions Nearest Neighbors), an ultra-scalable graph construction algorithm that avoids this ``search bottleneck’’ that existing graph-based me

Sources: