This inventor holds 1 USPTO granted patent and 1 published patent application. Top assignee: Visa International Service Association. Active years: 2026.
Data source: USPTO (United States Patent and Trademark Office) public patent records. Weekly synchronization. How IDiyas builds this profile
Company Filing History:
Years Active: 2026
Title: Yuchen Yan: Inventor of a Universal-Depth Graph Neural Network
Introduction
Yuchen Yan is an inventor based in Urbana, Illinois, whose patent work concerns graph neural networks. His listed patent focuses on a method for training networks with a trainable depth parameter.
Latest Patents
Yan is associated with 1 patent, titled “Method, System, and Computer Program Product for Universal Depth Graph Neural Networks.” The invention describes obtaining a graph represented by an adjacency matrix and an attribute matrix, then training a graph convolutional network using an updating equation. In that equation, the output embedding matrix is computed using a nonlinear activation function, a filter, the attribute matrix, a trainable weight matrix, and a trainable depth parameter.
Career Highlights
Yan is associated with Visa International Service Association. His patent reflects work on graph-learning methods designed to support universal-depth neural networks.
Collaborations
Yuzhong Chen and Mahashweta Das are identified as Yan’s coworkers.
Conclusion
Yuchen Yan’s patent centers on a graph neural network approach that incorporates trainable depth, connecting his inventive work with his professional association at Visa International Service Association.
Data source: USPTO (United States Patent and Trademark Office) public patent records. Weekly synchronization. How IDiyas builds this profile