US Patent Issued to International Business Machines on Dec. 23 for "Adaptive self-adversarial negative sampling for graph neural network training" (California, New York Inventors)

ALEXANDRIA, Va., Dec. 23 -- United States Patent no. 12,505,350, issued on Dec. 23, was assigned to International Business Machines Corp. (Armonk, N.Y.).

"Adaptive self-adversarial negative sampling for graph neural network training" was invented by Xiao Qin (San Jose, Calif.), Nasrullah Sheikh (San Jose, Calif.), Berthold Reinwald (San Jose, Calif.) and Lingfei Wu (Elmsford, N.Y.).

According to the abstract* released by the U.S. Patent & Trademark Office: "A graph neural network (GNN) training method, system, and computer program product in a graph, include generating, by the computing device, one or more one or more hypothetical edges between two or more nodes of a plurality of nodes of a graph neural network, testing, by the computing ...