Updatable Balanced Index for Stable Streaming

A 2026 research paper on streaming approximate nearest neighbor search with in-place graph index updates. The approach enables real-time index modifications without expensive rebuilds, crucial for dynamic datasets.

An ultra-scalable graph-based nearest neighbor indexing algorithm that builds state-of-the-art indexes up to 11.6× faster than Vamana (DiskANN) and 12.9× faster than HNSW. PiPNN uses HashPrune, a novel online pruning algorithm that enables efficient billion-scale index construction on a single machine.

Fast and accurate graph-based ANN index for streaming similarity search, enabling real-time updates on billion-point indexes using a single machine with real-time freshness.

Real-time indexing of vectors as they arrive in a stream, enabling immediate searchability without batch processing delays. Critical for applications requiring up-to-the-second freshness like social media, news, or real-time recommendations.

Research paper presenting IDEA, an inverted deduplication-aware index that compares physical vs. logical indexing approaches for vector search. Published at the 22nd USENIX Conference on File and Storage Technologies (FAST 24) in 2024.

NeurIPS 2023 paper proposing SOAR, a method for improved indexing in approximate nearest neighbor search, focusing on better space partitioning and search optimization.