Minji Yoon

Title: Minji Yoon: Innovator in Graph Neural Networks

Introduction

Minji Yoon is a prominent inventor based in Pittsburgh, PA (US). She has made significant contributions to the field of graph neural networks, showcasing her expertise through her innovative patent.

Latest Patents

Minji Yoon holds a patent titled "Performance-adaptive sampling strategy towards fast and accurate graph neural networks." This patent provides techniques for implementing a performance-adaptive sampling strategy that enhances the speed and accuracy of graph neural networks. The process involves storing a graph with multiple nodes and edges, initializing embeddings for each node, and employing machine learning techniques to train the graph neural network. The method includes selecting neighbors based on a sampling policy, computing performance loss, and modifying the sampling policy based on the gradient of the performance loss.

Career Highlights

Minji Yoon is currently associated with Microsoft Technology Licensing, LLC, where she applies her skills and knowledge in the development of advanced technologies. Her work focuses on improving the efficiency and effectiveness of machine learning applications.

Collaborations

Minji collaborates with talented individuals such as Jaewon Yang and Sufeng Niu, contributing to a dynamic and innovative work environment.

Conclusion

Minji Yoon's contributions to graph neural networks and her innovative patent reflect her dedication to advancing technology. Her work at Microsoft Technology Licensing, LLC, along with her collaborations, positions her as a key player in the field of machine learning.