Ping Li

D689365, Sep 10, 2013

Aug 15, 2012

29/429741

Ping Li - Los Angeles CA, US

0907

D 9451

20210133246, May 6, 2021

Sep 27, 2020

17/033791

- Sunnyvale CA, US
Zhixin ZHOU - Los Angeles CA, US
Zhaozhuo XU - Houston TX, US
Ping LI - Bellevue WA, US

Baidu USA LLC - Sunnyvale CA

G06F 16/901
G06F 17/16
G06F 16/903

Presented herein are embodiments of a fast search on graph methodology for Maximum Inner Product Search (MIPS). This optimization problem is challenging since traditional Approximate Nearest Neighbor (ANN) search methods may not perform efficiently in the nonmetric similarity measure. Embodiments herein are based on the property that a Möbius/Möbius-like transformation introduces an isomorphism between a subgraph of -Delaunay graph and Delaunay graph for inner product. Under this observation, embodiments of a novel graph indexing and searching methodology are presented to find the optimal solution with the largest inner product with the query. Experiments show significant improvements compared to existing methods.

20210117459, Apr 22, 2021

Sep 16, 2020

17/023283

- Sunnyvale CA, US
Zhixin ZHOU - Los Angeles CA, US
Zhaozhuo XU - Houston TX, US
Ping LI - Bellevue WA, US

Baidu USA LLC - Sunnyvale CA

G06F 16/33
G06F 16/901
G06K 9/62

Retrieval of relevant vectors produced by representation learning can critically influence the efficiency in Natural Language Processing (NLP) tasks. Presented herein are systems and methods for searching vectors via a typical nonmetric matching function: inner product. Embodiments, which construct an approximate Inner Product Delaunay Graph (IPDG) for top-1 Maximum Inner Product Search (MIPS), transform retrieving the most suitable latent vectors into a graph search problem with great benefits of efficiency. Experiments on data representations learned for different machine learning tasks verify the outperforming effectiveness and efficiency of IPDG embodiments.