ALEXANDRIA, Va., Jan. 20 -- United States Patent no. 12,530,435, issued on Jan. 20, was assigned to Rakuten Group Inc. (Tokyo).
"One-class recommender system with hinge pairwise distance loss and orthogonal representations" was invented by Ramin Raziperchikolaei (San Mateo, Calif.).
According to the abstract* released by the U.S. Patent & Trademark Office: "Known methods for training a recommender system rely on both similar and dissimilar user-item pairs. Using dissimilar pairs introduces several challenges, such as increasing training time or labeling pairs with unknown interactions as dissimilar even though the user may like the item if presented with it. If only similar pairs are used in the known methods, the result is a collapsed so...