Ken Ziyu Liu’s Home Page

About Me

I’m currently an MS research student at Carnegie Mellon University, co-advised by Prof. Virginia Smith and Prof. Artur Dubrawski. Before CMU, I spent some time at Google Research where I was fortunate to work closely with Peter Kairouz and Jakub Konečný on federated learning. Before that, I did my undergrad in computer science at the University of Sydney, where I was advised by Prof. Wanli Ouyang and received First Class Honours and the University Medal. I’ve also worked on various things at Apple, AWS, and Facebook.

I am broadly interested in developing practical intelligent systems. My current exploration focuses on privacy-preserving machine learning via federated learning and differential privacy. I am also interested in computer vision, deep learning, and theory.

Email / LinkedIn / GitHub / Google Scholar

Research

(*equal contribution, ^†alphabetical authorship)

	The Skellam Mechanism for Differentially Private Federated Learning Naman Agarwal^†, Peter Kairouz^†, Ziyu Liu^† NeurIPS 2021: Conference on Neural Information Processing Systems Oral Presentation at PPML 2021 PDF / Abstract / BibTeX / Code / Talk 1 / Talk 2 `@article{agarwal2021skellam, title={The Skellam Mechanism for Differentially Private Federated Learning}, author={Agarwal, Naman and Kairouz, Peter and Liu, Ziyu}, journal={arXiv preprint arXiv:2110.04995}, year={2021} }`
	The Distributed Discrete Gaussian Mechanism for Federated Learning with Secure Aggregation Peter Kairouz^†, Ziyu Liu^†, Thomas Steinke^† ICML 2021: International Conference on Machine Learning Oral Presentation at TPDP 2021 PDF / Abstract / Short Ver. / BibTeX / Code / Talk `@article{kairouz2021distributed, title={The Distributed Discrete Gaussian Mechanism for Federated Learning with Secure Aggregation}, author={Kairouz, Peter and Liu, Ziyu and Steinke, Thomas}, journal={arXiv preprint arXiv:2102.06387}, year={2021} }`
	Learning Implicit Credit Assignment for Cooperative Multi-Agent Reinforcement Learning Meng Zhou, Ziyu Liu, Pengwei Sui, Yixuan Li, Yuk Ying Chung NeurIPS 2020: Conference on Neural Information Processing Systems PDF / BibTeX / Code `@article{zhou2020learning, title={Learning Implicit Credit Assignment for Cooperative Multi-Agent Reinforcement Learning}, author={Zhou, Meng and Liu, Ziyu and Sui, Pengwei and Li, Yixuan and Chung, Yuk Ying}, journal={arXiv preprint arXiv:2007.02529}, year={2020} }`
	Disentangling and Unifying Graph Convolutions for Skeleton-Based Action Recognition Ziyu Liu, Hongwen Zhang, Zhenghao Chen, Zhiyong Wang, Wanli Ouyang CVPR 2020: Conference on Computer Vision and Pattern Recognition Oral Presentation PDF / Abstract / Supp / BibTeX / Demo / Code Star `@inproceedings{liu2020disentangling, title={Disentangling and Unifying Graph Convolutions for Skeleton-Based Action Recognition}, author={Liu, Ziyu and Zhang, Hongwen and Chen, Zhenghao and Wang, Zhiyong and Ouyang, Wanli}, booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition}, pages={143--152}, year={2020} }`

Teaching

I have been a teaching assistant for the following courses at the University of Sydney:

COMP9110 System Analysis and Modelling, 2020
COMP3027 Algorithm Design, 2018
SOFT2412 Agile Software Development Practices, 2019
COMP2017 Systems Programming, 2018
INFO1103 Intro to Programming, 2017

Experience

Google AI Resident, Present
Facebook, Menlo Park, United States Software Engineer Intern, Messenger Ranking, 2019/2020
Amazon Web Services, Sydney, Australia Software Engineer Intern, Safety Engineering, 2018/2019
Apple, Cupertino, United States Software Engineer Intern, Core OS, 2018

Professional Service

I’m serving as a reviewer for:

CVPR 2022: IEEE/CVF Conference on Computer Vision and Pattern Recognition
IJCV 2021: International Journal of Computer Vision