US Patent Issued to Huawei Technologies'Co., 'Ltd.' on June 30 for "System, method, and computer-readable media for leakage correction in graph neural network based recommender systems" (Canadian Inventors)

ALEXANDRIA, Va., July 16 -- United States Patent no. 12,670,387, issued on June 30, was assigned to Huawei Technologies'Co.'Ltd.' (Shenzhen, China).

"System, method, and computer-readable media for leakage correction in graph neural network based recommender systems" was invented by Ishaan Kumar (Montreal), Yaochen Hu (Westmount, Canada) and Yingxue Zhang (Montreal).

According to the abstract* released by the U.S. Patent & Trademark Office: "Systems, methods, and computer-readable media provide a graph processing system that incorporates a graph neural network (GNN) based recommender system (RS), as well as a method for training a GNN based RS to address feature leakage that leads to overfitting of the trained GNN based RS. A message corr...