π About
Iβm currently an MS research student (MSR) at Carnegie Mellon University working on the intersection of machine learning and privacy & security. Iβm very fortunate to be co-advised by Prof. Virginia Smith and Prof. Artur Dubrawski and also working with Prof. Steven Wu.
Before CMU, I spent a year at Google Research where I led the efforts to deploy our distributed DP via SecAgg algorithms [1, 2] to mobile devices and as part of TensorFlow. I had the fortune to work closely with Peter Kairouz, Jakub KoneΔnΓ½, Thomas Steinke, and Naman Agarwal.
Before Google, I did my undergrad in computer science at University of Sydney, was advised by Prof. Wanli Ouyang, and received First-Class Honours and the University Medal. I also designed, built, and shipped various things at Apple, AWS, and Meta.
I like to build and understand ML methods and systems that are simple, practical, and can be responsibly deployed in the real world. My current research focuses on ML privacy, primarily working with differential privacy and federated learning. Iβm also interested in deep learning, ML systems, computer vision, and theory.
Email / LinkedIn / GitHub / Google Scholar / Twitter
π₯ Recent News
- Mar 2023: I led our awesome CMU team ("puffle") to win 1st place at the U.S. Privacy-Enhancing Technologies (PETs) Prize Challenge, Pandemic Forecasting Track (USD $100,000). We are featured by the White House, U.K. Government, Summit for Democracy, DrivenData, and NSF. Details and blogpost coming soon :).
- Mar 2023: Our research [1,2] on distributed differential privacy for federated learning is officially deployed to Android and featured on the Google AI blog π
- Jan 2023: DP2 is accepted to ICLR'23 and also presented as an oral presentation at OPT 2022. Check out our code!
- Nov 2022: I'll be in-person at NeurIPS in New Orleans, excited to meet people around! We are showcasing three papers: private silos, Motley, and DP2.
- Sept 2022: Our paper on private cross-silo FL will be presented at NeurIPS this year
- Aug 2022: I gave a talk about private cross-silo FL at Google Research and presented it at TPDP 2022
- Jun 2022: We released Motley, a benchmark for heterogeneous and personalized federated learning and will present it at FL-NeurIPS'22 [code]
π Papers
![]() | Differentially Private Adaptive Optimization with Delayed Preconditioners ![]() Tian Li, Manzil Zaheer, Ziyu Liu, Sashank Reddi, Brendan McMahan, Virginia Smith ICLR 2023: International Conference on Learning Representations Oral Presentation at OPT 2022 of NeurIPS'22 PDF / BibTeX / Code |
![]() | On Privacy and Personalization in Cross-Silo Federated Learning ![]() Ziyu Liu, Shengyuan Hu, Zhiwei Steven Wu, Virginia Smith NeurIPS 2022: Conference on Neural Information Processing Systems Presented at TPDP 2022 of ICML'22 PDF / BibTeX / Code / Poster |
![]() | Motley: Benchmarking Heterogeneity and Personalization in Federated Learning ![]() Shanshan Wu, Tian Li, Zachary Charles, Yu Xiao, Ziyu Liu, Zheng Xu, Virginia Smith Preprint Presented at FL-NeurIPS'22 PDF / BibTeX / Code |
![]() | 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 of ACM CCS'21 PDF / BibTeX / Code / Talk 1 / Talk 2 / Poster / Slides |
![]() | 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 of ICML'21 Full PDF / Short PDF / BibTeX / Code / Talk / Poster / Slides |
![]() | 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 Presented at RL Theory Workshop of ICML'20 PDF / BibTeX / Code |
![]() ![]() | 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 / Supp / BibTeX / Demo / Code Star |
π Professional Service
Iβm serving as a conference/journal reviewer for:
- ICCV 2023: International Conference on Computer Vision
- ICML 2023: International Conference on Machine Learning
- CVPR 2023: IEEE/CVF Conference on Computer Vision and Pattern Recognition
- AISTATS 2023: International Conference on Artificial Intelligence and Statistics
- NeurIPS 2022: Conference on Neural Information Processing Systems
- TIP 2022: IEEE Transactions on Image Processing
- ECCV 2022: European Conference on Computer Vision
- CVPR 2022: IEEE/CVF Conference on Computer Vision and Pattern Recognition
- IJCV 2021: International Journal of Computer Vision
πΌ Experience
Carnegie Mellon University, Pittsburgh, United States Research Assistant (RI/MLD), 2021-present | ![]() |
Google Research (remote from Sydney) AI Resident Researcher, 2020-2021 (Left early for grad school deferred from 2020) | |
Facebook, Menlo Park, United States Software Engineer Intern, Messenger Ranking, Winter 2019/2020 (Summer in π¦π¦πΊ) | |
Amazon Web Services, Sydney, Australia Software Engineer Intern, Safety Engineering, Winter 2018/2019 (Summer in π¦π¦πΊ) | |
Apple, Cupertino, United States Software Engineer Intern, Core OS, Summer 2018 | ![]() |
π§βπ» Teaching
I have been a teaching assistant (academic tutor) for the following classes while an undergrad at USyd:
- 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
β Misc
- In my free time, I try to read, hike, lift weights, and Dota 2, among other things
- On the side, I advised/part-timed with DynamoFL, a YC startup working on deploying federated learning
- Twitter, Mastodon, Instagram