Reviews: Möbius Transformation for Fast Inner Product Search on Graph
–Neural Information Processing Systems
This paper proposed a new algorithm for max-inner-product-search, a widely encountered problem in all kinds of applications. Though seemingly similar to ANN problem, MIPS is different in terms of theory and algorithm design, so that the massive amount of KNN methods cannot apply directly. The authors extend the well-known Delaunay graph type of methods in ANN to MIPS and provide both theoretical discussion and experimental evidence to show the advantage of the proposed method. I find this paper to be interesting, and would like the authors to consider my following comments: 1. For assumption 1, I'm a little confused.
Neural Information Processing Systems
Jan-21-2025, 14:35:50 GMT
- Technology: