ICML 2020 paper introducing ScaNN (Scalable Nearest Neighbors), a system for accelerating large-scale vector similarity search using anisotropic vector quantization, combining quantization with asymmetric distance computation for high-performance ANN search.
Loading more......
On this page
ScaNN — Accelerating Large-Scale Inference with Anisotropic Vector Quantization
ScaNN introduces anisotropic vector quantization combined with asymmetric distance computation for fast large-scale vector similarity search.
ScaNN became a core component of Google's large-scale retrieval systems, enabling fast semantic search and recommendation at scale.
Explore more items related to this one