Hanqing Zeng

RESEARCH SCIENTIST | MENLO PARK, UNITED STATES

I am a Research Scientist at Meta, where I work on efficient graph learning models for web-scale social recommendation. Prior to Meta, I obtained my Ph.D. in Computer Engineering at University of Southern California. My thesis focused on improving the scalability, accuracy and efficiency of large scale Graph Neural Networks. I designed new neural network models, learning algorithms as well as hardware systems for GNN training and inference. My work has led to publications in top venues in both AI (ICLR, NeurIPS, ICML, etc.) and systems (FPGA, VLDB, TPDS, etc.). I have received outstanding reviewer awards from ICLR and ICML.

Hanqing's Work

Hanqing's Publications

February 15, 2024

RANKING AND RECOMMENDATIONS

CORE MACHINE LEARNING

TASER: Temporal Adaptive Sampling for Fast and Accurate Dynamic Graph Representation Learning

Danny Deng, Hongkuan Zhou, Rajgopal Kannan, Viktor Prasanna, Hanqing Zeng, Chris Leung (AI), Jianbo Li, Yinglong Xia

February 15, 2024

August 21, 2023

SYSTEMS RESEARCH

GraphAGILE: An FPGA-Based Overlay Accelerator for Low-Latency GNN Inference

Bingyi Zhang, Viktor Prasanna, Hanqing Zeng

August 21, 2023

August 11, 2023

CORE MACHINE LEARNING

Generative Graph Dictionary Learning

Zhichen Zeng, Ruike Zhu, Hanghang Tong, Hanqing Zeng, Yinglong Xia

August 11, 2023