About
I’m a 1st-year PhD student at Stanford Computer Science and Stanford AI Lab, rotating with Prof. Dan Boneh at Applied Cryptography Group, with Prof. Percy Liang at Stanford NLP, and with Prof. Sanmi Koyejo at Stanford Trustworthy AI Research (STAIR). I’m supported in part by Stanford School of Engineering Fellowship.
Before Stanford, I did my MS thesis at Carnegie Mellon University (RI/MLD) on differential privacy and federated learning and led the CMU team to a 1st place at the US-UK Privacy-Enhancing Technologies Challenge. I was very fortunate to be co-advised by Prof. Virginia Smith, Artur Dubrawski, and Steven Wu.
Before grad school, I was at Google AI/Research working on distributed differential privacy algorithms [1, 2] and led the efforts to deploy them to Android devices and TensorFlow. I worked closely with Peter Kairouz, Jakub Konečný, Thomas Steinke, and Naman Agarwal.
Before Google, I did my undergrad at University of Sydney, where I worked with Wanli Ouyang and received First Class Honours and the University Medal. During my undergrad, I designed and shipped various things at Apple, AWS, and Meta.
I am interested in the privacy, security, localization, and trustworthiness aspects of current AI systems and their interplay. More broadly, I like to build, understand, and apply machine learning methods and systems that are simple, practical, and trustworthy.
Blog / GitHub / Google Scholar / LinkedIn / Twitter
Feel free reach out for research, collaborations, or a casual chat, especially if you are a junior, disadvantaged, or underrepresented student. Also consider giving me anonymous feedback.
Recent News
- Jan 2024: Check out our recent report (tweet) on the effects of data contamination in language models!
- Aug 2023: Spent five weeks teaching programming & algorithms in Ethiopia as part of AddisCoder 🇪🇹!
- July 2023: Gave a talk at NITRD Privacy R&D Interagency Working Group
- June 2023: Gave a talk about model personalization at SWIFT
- May 2023: Gave a talk about our entry to the PETs challenge at the Royal Society in London, UK
- Mar 2023: I led our awesome CMU team ("puffle") to win 1st place at the US-UK Privacy-Enhancing Technologies (PETs) Prize Challenge, Pandemic Forecasting Track (USD $100,000). See news by the White House, UK Government, Summit for Democracy, DrivenData, NSF, and CMU news!
- May 2023: We wrote a blog post about privacy and personalization in cross-silo FL and the recent PETs challenge on ML@CMU. Check out the extended version if you're feeling adventurous.
- Mar 2023: Our research on distributed differential privacy for federated learning [1,2] is officially deployed to Android and featured on the Google AI blog!
- 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.
- Aug 2022: Gave a talk about private cross-silo FL at Google Research and presented it at TPDP 2022
Research & Papers
|
Investigating Data Contamination for Pre-training Language Models
Minhao Jiang, Ken Ziyu Liu, Ming Zhong, Rylan Schaeffer, Siru Ouyang, Jiawei Han, Sanmi Koyejo Tech Report PDF / BibTeX / Code / Tweet |
|
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 / Blog Post |
|
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 |
Teaching & Mentoring
I love teaching! Most recently, I was part of the teaching team of AddisCoder 2023 🇪🇹, an intensive summer school in Ethiopia for middle/high school students interested in programming and computer science. I helped create lab exercises, gave lab lectures, and graded exams. I was also the main IT guy responsible for managing 100+ lab machines and making sure students can do exercises under poor technical infrastructure.
I’m also involved in the following teaching/mentoring activities:
While an undergrad at USyd, I was a teaching assistant (academic tutor) for the following classes:
Professional Service
- Program Committee for Private ML-ICLR'24: Privacy Regulation and Protection in Machine Learning Workshop
- Reviewer for ICML 2024: International Conference on Machine Learning
- Reviewer for ICLR 2024: International Conference on Learning Representations
- Program Committee for FL-ICML'23: Workshop on Federated Learning and Analytics in Practice
- Reviewer for NeurIPS 2023: Conference on Neural Information Processing Systems
- Reviewer for ICCV 2023: International Conference on Computer Vision
- Reviewer for ICML 2023: International Conference on Machine Learning
- Reviewer for CVPR 2023: IEEE/CVF Conference on Computer Vision and Pattern Recognition
- Reviewer for AISTATS 2023: International Conference on Artificial Intelligence and Statistics
- Reviewer for NeurIPS 2022: Conference on Neural Information Processing Systems
- Reviewer for TIP 2022: IEEE Transactions on Image Processing
- Reviewer for ECCV 2022: European Conference on Computer Vision
- Reviewer for CVPR 2022: IEEE/CVF Conference on Computer Vision and Pattern Recognition
- Reviewer for IJCV 2021: International Journal of Computer Vision
Experience
Stanford Artificial Intelligence Laboratory (SAIL), Stanford CA, United States PhD student, 2023-Present |
|
Carnegie Mellon School of Computer Science, Pittsburgh PA, United States Research Assistant (RI/MLD), 2021-2023 |
|
Google Research (remote from Sydney) AI Resident Researcher, 2020-2021 (Left early for grad school deferred from 2020) |
|
Facebook, Menlo Park CA, United States Software Engineer Intern, Messenger Ranking, Winter 2019/2020 (Summer in 🦘🇦🇺) |
|
Amazon Web Services, Sydney, Australia Software Engineer Intern, Safety Engineering, Winter 2018/2019 (Summer in 🦘🇦🇺) |
|
Apple, Cupertino CA, United States Software Engineer Intern, Core OS, Summer 2018 |
|
☕ Misc
- In my free time, I try to read, travel, practice olympic lifts, bake cheesecakes, and Dota 2, among other things
- On the side, I advised/part-timed with DynamoFL, a YC startup working on federated learning
- Twitter, Mastodon, Instagram, Goodreads
- My Erdős number is 4 via three paths
- Consider using JAX! It's a beautiful thing
- Check out cs-sop.org if you're a prospective grad school applicant; I have benefited from this initiative and I have shared my statement there too
Visits since COVID: