Email: tianli@cmu.edu


     


Tian Li


I am a fifth-year PhD student in Computer Science Department at Carnegie Mellon University working with Virginia Smith. Prior to CMU, I received undergraduate degrees in Computer Science and Economics from Peking University in 2018.

My research centers around optimization, trustworthy machine learning, and learning in heterogeneous environments, with applications to federated learning. I am interested in designing, analyzing, and evaluating principled learning algorithms, taking into account real-world constraints (e.g., communication and heterogeneity) to address issues related to accuracy, scalability, trustworthiness (fairness, robustness, and privacy), and their interplays.

Research

Selected
All

Manuscripts

To Federate or Not To Federate: Incentivizing Client Participation in Federated Learning
Yae Jee Cho, Divyansh Jhunjhunwala, Tian Li, Virginia Smith, Gauri Joshi
[Arxiv]
A Field Guide to Federated Optimization
(50+ authors) Jianyu Wang, Zachary Charles, Zheng Xu, Gauri Joshi, H. Brendan McMahan, ..., Tian Li, ..., Virginia Smith, ...
[Arxiv]

Publications

On Tilted Losses in Machine Learning: Theory and Applications
Tian Li*, Ahmad Beirami*, Maziar Sanjabi, Virginia Smith
JMLR 2023
[Arxiv] [Code]
Differentially Private Adaptive Optimization with Delayed Preconditioners
Tian Li, Manzil Zaheer, Ken Ziyu Liu, Sashank Reddi, Brendan McMahan, Virginia Smith
ICLR 2023
[Arxiv] [Code]
Private Adaptive Optimization with Side Information
Tian Li, Manzil Zaheer, Sashank Reddi, Virginia Smith
ICML 2022
[Paper] [Arxiv] [Code] [Slides] [Poster]
Motley: Benchmarking Heterogeneity and Personalization in Federated Learning
Shanshan Wu, Tian Li, Zachary Charles, Yu Xiao, Ziyu Liu, Zheng Xu, Virginia Smith
Federated Learning Workshop, NeurIPS 2022
[Arxiv] [Code]
Diverse Client Selection for Federated Learning via Submodular Maximization
Ravikumar Balakrishnan*, Tian Li*, Tianyi Zhou*, Nageen Himayat, Virginia Smith, Jeff Bilmes
ICLR 2022
[Paper]
Federated Hyperparameter Tuning: Challenges, Baselines, and Connections to Weight-Sharing
Mikhail Khodak, Renbo Tu, Tian Li, Liam Li, Maria-Florina Balcan, Virginia Smith, Ameet Talwalkar
NeurIPS 2021
[Paper] [Arxiv] [Code]
Tilted Empirical Risk Minimization
Tian Li*, Ahmad Beirami*, Maziar Sanjabi, Virginia Smith
ICLR 2021
[Paper] [Arxiv] [Code] [Slides] [Poster] [Blog post]
Ditto: Fair and Robust Federated Learning Through Personalization
Tian Li, Shengyuan Hu, Ahmad Beirami, Virginia Smith
ICML 2021
Best Paper Award at ICLR 2021 Secure ML Workshop
[Paper] [Arxiv] [Code] [Slides] [Poster] [Video] [Longer Talk]
Heterogeneity for the Win: One-Shot Federated Clustering
Don Kurian Dennis, Tian Li, Virginia Smith
ICML 2021
[Paper] [Arxiv]
Ease.ML: A Lifecycle Management System for MLDev and MLOps
(20 authors) ..., Tian Li, ..., Wentao Wu, Ce Zhang
CIDR 2021
[Paper] [Ce's talk]
Federated Optimization in Heterogeneous Networks
Tian Li, Anit Kumar Sahu, Manzil Zaheer, Maziar Sanjabi, Ameet Talwalkar, Virginia Smith
MLSys 2020
[Paper] [Arxiv] [Code] [Slides] [Poster] [Video]
Fair Resource Allocation in Federated Learning
Tian Li, Maziar Sanjabi, Ahmad Beirami, Virginia Smith
ICLR 2020
[Paper] [Arxiv] [Code] [Slides] [Video]
Federated Learning: Challenges, Methods, and Future Directions
Tian Li, Anit Kumar Sahu, Ameet Talwalkar, Virginia Smith
IEEE Signal Processing Magazine, Special Issue on Distributed, Streaming Machine Learning, 2020
The Most Popular SPM Article of 2020   (Link)
[Paper] [Arxiv] [Blog post]
Learning Context-aware Policies from Multiple Smart Homes via Federated Multi-Task Learning
Tianlong Yu, Tian Li, Yuqiong Sun, Susanta Nanda, Virginia Smith, Vyas Sekar, Srinivasan Seshan
IoTDI 2020
[Paper]
FedDANE: A Federated Newton-Type Method
Tian Li, Anit Kumar Sahu, Manzil Zaheer, Maziar Sanjabi, Ameet Talwalkar, Virginia Smith
Asilomar Conference on Signals, Systems and Computers 2019 (Invited Paper)
[Paper] [Arxiv] [Code]
LEAF: A Benchmark for Federated Settings
Sebastian Caldas, Sai Meher Karthik Duddu, Peter Wu, Tian Li, Jakub Konecny, H. Brendan McMahan, Virginia Smith, Ameet Talwalkar
Federated Learning Workshop, NeurIPS 2019
[Website] [Arxiv]

Ease.ml: Towards Multi-Tenant Resource Sharing for Machine Learning Workloads
Tian Li, Jie Zhong, Ji Liu, Wentao Wu, Ce Zhang
VLDB 2018
[Paper] [Arxiv]
CUTE: Query Knowledge Graphs by Tabular Examples
Zichen Wang*, Tian Li*, Yingxia Shao, Bin Cui
WAIM 2018 (demo)
[Paper] [Poster]
An Overreaction to the Broken Machine Learning Abstraction: The ease.ml Vision
Ce Zhang, Wentao Wu, Tian Li
HILDA Workshop, SIGMOD 2017
[Paper]

Talks

Learning in Heterogeneous Networks: Optimization and Fairness
Federated Learning One World (FLOW) Seminar
[Video]
Fair and Robust Federated Learning Through Personalization
TrustML Young Scientists Seminar
[Video (the first half)]
        

© 2023 Tian Li.