Cheng Zheng

Title:

Inventor Spotlight: Cheng Zheng - Revolutionizing Graph Sparsification

Introduction:

Cheng Zheng, a prolific inventor based in Los Angeles, CA, has made significant contributions to the field of graph sparsification. With a total of 2 patents under his belt, Cheng Zheng's innovative work has paved the way for advancements in deep learning and graph-based data analysis.

Latest Patents:

1. Deep Graph De-noise by Differentiable Ranking: Cheng Zheng's groundbreaking method involves the use of a differentiable ranking based graph sparsification (DRGS) network to leverage supervision signals from downstream tasks for graph sparsification. The method combines neighborhood aggregation operators, sparsified subgraph generation, task feeding, and error minimization to enhance prediction accuracy and model performance.

2. Method for Supervised Graph Sparsification: Cheng Zheng's second patent introduces a method for employing a supervised graph sparsification (SGS) network to utilize feedback from subsequent graph learning tasks for guided graph sparsification. This approach involves edge sampling, prediction/classification error collection, and parameter updates to optimize graph sparsification in both training and testing phases.

Career Highlights:

Currently affiliated with NEC Corporation, Cheng Zheng's technical expertise and inventive spirit have positioned him as a key figure in the research and development of advanced graph sparsification techniques. His dedication to pushing the boundaries of machine learning and data analysis has earned him recognition in the industry.

Collaborations:

Cheng Zheng has had the privilege of collaborating with esteemed colleagues such as Bo Zong and Haifeng Chen. Together, they have worked on cutting-edge projects that have garnered attention for their innovative approaches to graph sparsification and machine learning applications.

Conclusion:

Inventor Cheng Zheng's relentless pursuit of excellence and novel solutions in the realm of graph sparsification showcases his commitment to driving innovation in the field of data science. His patents stand as a testament to his ingenuity and the impact of his work on shaping the future of machine learning algorithms and graph-based methodologies.