4 papers
PiPNN: Ultra-Scalable Graph-Based Nearest Neighbor Indexing
Tobias Rubel, Richard Wen, Laxman Dhulipala +3
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…
Efficiently Constructing Sparse Navigable Graphs
Alex Conway, Laxman Dhulipala, Martin Farach-Colton +6
Graph-based nearest neighbor search methods have seen a surge of popularity in recent years, offering state-of-the-art performance across a wide variety of applications. Central to…
In-Place Updates of a Graph Index for Streaming Approximate Nearest Neighbor Search
Haike Xu, Magdalen Dobson Manohar, Philip A. Bernstein +3
Indices for approximate nearest neighbor search (ANNS) are a basic component for information retrieval and widely used in database, search, recommendation and RAG systems. In these…
Adaptive Quotient Filters
Richard Wen, Hunter McCoy, David Tench +6
Adaptive filters, such as telescoping and adaptive cuckoo filters, update their representation upon detecting a false positive to avoid repeating the same error in the future. Adap…