Chenhui Deng
I have earned my PhD degree at Cornell University in May, 2024. My PhD research focuses on solving real-world problems on large-scale graph-structured data, specifically including circuit problems. My research area is in the interdisciplinary field of Machine Learning, Spectral Graph Theory, Electronic Design Automation, and VLSI. I am currently a Research Scientist at NVIDIA working on Large Language Models (LLM) and graph learning for chip design.
Email cd574@cornell.edu
Office Rhodes Hall 471D, Ithaca, NY, 14853
Resume CV
News
2024-03 Happy to present our recent progress about representation learning on computation graphs at CDSC, UCLA. |
2024-02 Thrilled to share that I have successfully passed my thesis defense! I would like to express my sincere appreciation to my family, teachers, friends, and all who have faith in me. |
2023-04 Happy to give a guest lecture at Cornell ECE 6980 on the topic of graph learning |
2022-08 Thrilled to share that I have won the prestigious and highly competitive 2022 Qualcomm Innovation Fellowship! There are only 19 teams winning the award out of 132 teams in North America this year. |
2022-05 Excited to announce that I have passed my A exam and become a PhD candidate now! Thanks all my committee members for their kind support and invaluable advice! |
Publications
GraphZoom: A Multi-Level Spectral Approach for Accurate and Scalable Graph Embedding (Oral, Acceptance Rate: 1.8%)
International Conference on Learning Representations (ICLR),
2020
|
|
GARNET: Reduced-Rank Topology Learning for Robust and Scalable Graph Neural Networks (SpotLight, Acceptance Rate: 4.6%)
Learning on Graphs Conference (LoG),
2022
|
|
Polynormer: Polynomial-Expressive Graph Transformer in Linear Time
International Conference on Learning Representations (ICLR)
2024
|
|
Less is More: Hop-Wise Graph Attention for Scalable and Generalizable Learning on Circuits
Design Automation Conference (DAC)
2024
|
|
Accurate Operation Delay Prediction for FPGA HLS Using Graph Neural Networks
IEEE/ACM International Conference on Computer-Aided Design (ICCAD),
2020
|
|
SPADE: A Spectral Method for Black-Box Adversarial Robustness Evaluation
International Conference on Machine Learning (ICML),
2021
|
|
Layout Symmetry Annotation for Analog Circuits with Graph Neural Networks
IEEE/ACM Asia and South Pacific Design Automation Conference (ASPDAC),
2021
|
|
GLAIVE: Graph Learning Assisted Instruction Vulnerability Estimation
IEEE/ACM Design Automation and Test in Europe (DATE),
2021
|
|
Book Chapters
Machine Learning for Agile FPGA Design
Machine Learning Applications in Electronic Design Automation, ed. H. Ren and J. Hu, Springer,
2022
|
|