Gangda (Danny) Deng

CS Ph.D. student @ USC

Github: @Hydrapse

Email me: gangdade@usc.edu

About Me

I am a 2nd-year Ph.D. student in Computer Science at University of Southern California, supervised by Prof. Viktor Prasanna. Before that, I got my B.S. degree from Central South University, advised by Prof. Ning Gui.

My research interest is to improve the accuracy, efficiency, and scalability of graph learning from the perspective of ML algorithms and software systems. Specifically, I focus on the following areas:

Publications (* Equal Contribution)

Gangda Deng, Hongkuan Zhou, Rajgopal Kannan, Viktor Prasanna
Learning Personalized Scoping for Graph Neural Networks under Heterophily.
ARXIV 2024

Yi-Chien Lin*, Gangda Deng*, Viktor Prasanna
A Unified CPU-GPU Protocol for GNN Training. Code
CF 2024

Gangda Deng*, Hongkuan Zhou*, Hanqing Zeng, Yinglong Xia, Christopher Leung, Jianbo Li, Rajgopal Kannan, Viktor Prasanna
TASER: Temporal Adaptive Sampling for Fast and Accurate Dynamic Graph Representation Learning. CodeSlides
IPDPS 2024

Gangda Deng*, Ömer Faruk Akgül*, Hongkuan Zhou, Hanqing Zeng, Yinglong Xia, Jianbo Li, Viktor Prasanna
An Efficient Distributed Graph Engine for Deep Learning on Graphs. CodeSlides
MLG-HPCE Workshop at SC 2023

Chenhuan Yu, Gangda Deng, Ning Gui
PairGNNs: enabling graph neural networks with pair-based view
Neural Computing and Applications 2023