Miryeong Kwon

Title: Miryeong Kwon: Innovator in Computing and Graph Neural Networks

Introduction

Miryeong Kwon is a prominent inventor based in Incheon, South Korea. He has made significant contributions to the fields of computing and graph neural networks, holding a total of 9 patents. His innovative work focuses on enhancing the efficiency and reliability of computing devices.

Latest Patents

One of Kwon's latest patents is a method of supporting persistence in computing devices. This invention involves a processor that executes instructions stored in a non-volatile memory module. It performs a stop procedure during power failures and a go procedure upon power recovery. The processor manages process control blocks, schedules processes, and executes idle tasks to ensure smooth operation during power interruptions.

Another notable patent is the method and apparatus for accelerating graph neural network (GNN) pre-processing. This invention includes a set-partitioning accelerator that sorts edges of an original graph, performs radix sorting, and conducts uniform random sampling on nodes. The apparatus efficiently generates a sorted COO array and converts edges into a compressed sparse row format, significantly enhancing GNN processing speed.

Career Highlights

Kwon has worked with notable organizations such as Memray Corporation and the Korea Advanced Institute of Science and Technology. His experience in these institutions has allowed him to develop and refine his innovative ideas, contributing to advancements in technology.

Collaborations

Throughout his career, Kwon has collaborated with talented individuals, including Myoungsoo Jung and Gyuyoung Park. These partnerships have fostered a creative environment that has led to groundbreaking inventions.

Conclusion

Miryeong Kwon's contributions to computing and graph neural networks exemplify his innovative spirit and dedication to advancing technology. His patents reflect a commitment to improving device reliability and processing efficiency.