“SCaNN: Accelerating Large-Scale Inference With Anisotropic Vector Quantization”, 2019-08-27 (; similar):
Quantization-based techniques are the current state-of-the-art for scaling maximum inner product search to massive databases. Traditional approaches to quantization aim to minimize the reconstruction error of the database points.
Based on the observation that for a given query, the database points that have the largest inner products are more relevant, we develop a family of anisotropic quantization loss functions. Under natural statistical assumptions, we show that quantization with these loss functions leads to a new variant of vector quantization that more greatly penalizes the parallel component of a datapoint’s residual relative to its orthogonal component.
osed approach achieves state-of-the-art results on the public benchmarks available at
ann-benchmarks.com.