This paper suggests the use of projective clustering based product quantization for improving nearest neighbor and max-inner-product vector search (MIPS) algorithms. We provide anisotropic and quantized variants of projective clustering which outperform previous clustering methods used for this problem such as ScaNN. We show that even with comparable running time complexity, in terms of lookup-multiply-adds, projective clustering produces more quantization centers resulting in more accurate dot-product estimates. We provide thorough experimentation to support our claims.

翻译：本文建议使用基于投影集成的产品量化法改进最近的近邻和最大产品矢量搜索算法。 我们提供了远方和量化的投影集成变种,这些变种优于以前用于这一问题的群集方法,如ScANN。 我们显示,即使运行时间相当复杂,在外观-倍增方面,投影集成产生更多的量化中心,从而得出更准确的点产品估计值。我们提供了支持我们索赔的彻底实验。