† for student author advised/mentored
Journal Papers:
[J16] On the Convergence Rates of Federated Q-Learning across Heterogeneous Environments,
Muxing Wang†, Pengkun Yang, and Lili Su
major revision at Transactions on Machine Learning Research (TMLR)
[J15] Empowering Federated Learning with Implicit Gossiping: Mitigating Connection Unreliability Amidst Unknown and Arbitrary Dynamics,
Ming Xiang†, Stratis Ioannidis, Edmund Yeh, Carlee Joe-Wong, and Lili Su
accepted to IEEE Signal Processing (TSP)
[J14] Fast and Robust State Estimation and Tracking via Hierarchical Learning,
Connor Mclaughlin†, Matthew Ding†, Deniz Edogmus, and Lili Su
minor revision at IEEE Transactions on Automatic Control (TAC)
[J13] Global Convergence of Federated Learning for Mixed Regression,
Lili Su, Jiaming Xu, and Pengkun Yang,
IEEE Transactions on Information theory (TIT), 2024
[J12] Towards Safe Autonomy in Hybrid Traffic: Detecting Unpredictable Abnormal Behaviors of Human Drivers via Information Sharing,
Jiangwei Wang†, Lili Su, Songyang Han†, Dongjin Song, and Fei Miao,
ACM Transactions on Cyber-Physical Systems, 2024
[J11] A Non-Parametric View of FedAvg and FedProx: Beyond Stationary Points,
Lili Su, Jiaming Xu, and Pengkun Yang,
Journal of Machine Learning Research (JMLR), 2023
[J10] Experimental Design Networks: A Paradigm for Serving Heterogeneous Learners under Networking Constraints,’
Yuanyuan Li†, Yuezhou Liu†, Lili Su, Edmund Yeh, and Stratis Ioannidis,
IEEE/ACM Transactions on Networking (ToN), Feb. 2023
[J9] Byzantine-Resilient Multi-Agent Optimization [link]
Lili Su and Nitin H. Vaidya
IEEE Transactions on Automatic Control (TAC), May 2021.
[J8] Finite-Time Guarantees for Byzantine-Resilient Distributed State Estimation With Noisy Measurements [link]
Lili Su and Shahin Shahrampour
IEEE Transactions on Automatic Control (TAC), Sept. 2020.
[J7] Spike-Based Winner-Take-All Computation: Fundamental Limits and Order-Optimal Circuits [link]
Lili Su, Chia-Jung Chang, and Nancy Lynch
Neural Computation, Dec. 2019.
[J6] Collaboratively Learning the Best Option on Graphs, Using Bounded Local Memory [link]
Lili Su, Martin Zubeldia, and Nancy Lynch,
Proceedings of the ACM on Measurement and Analysis of Computing Systems, Volume 3, Issue 1, Mar. 2019.
[J5] Securing Distributed Gradient Descent in High Dimensional Statistical Learning [link]
Lili Su and Jiaming Xu,
Proceedings of the ACM on Measurement and Analysis of Computing Systems, Volume 3, Issue 1, Mar. 2019.
[J4] Defending non-Bayesian Learning in the Presence of Byzantine Adversaries [link]
Lili Su and Nitin H. Vaidya,
Distributed Computing, Springer, June 2018
[J3] Distributed Statistical Machine Learning in Adversarial Settings: Byzantine Gradient Descent [link]
Yudong Chen, Lili Su*, and Jiaming Xu,
Proceedings of the ACM on Measurement and Analysis of Computing Systems, Volume 1, Issue 2, Dec. 2017
* correspondence author
[J2] Computing similarity distances between rankings [link]
Farzad Farnoud (Hassanzadeh), Olgica Milenkovicc, Gregory J.Puleod, and Lili Su
Discrete Applied Mathematics, Dec. 2017.
[J1] Reaching approximate Byzantine consensus with multi-hop communication [link]
Lili Su and Nitin H.Vaidya
Information and Computation, Aug. 2017.
Conference Papers:
[C39] Data-efficient Trajectory Prediction via Coreset Selection,
Ruining Yang† and Lili Su,
submitted
arXiv: 2409.17385
A short version will be presented at AAAI 2025 Good Data Workshop
[C38] Building Real-time Awareness of Out-of-distribution in Trajectory Prediction for Autonomous Vehicles,
Tongfei (Felicia) Guo†, Taposh Banerjee, Rui Liu, and Lili Su,
submitted
arXiv: 2409.17277
[C37] Reactive Multi-Robot Navigation in Outdoor Environments Through Uncertainty-Aware Active
Learning of Human Preference Landscape,
Chao Huang†, Wenshuo Zang†, Carlo Pinciroli, Zhi Jane Li, Taposh Banerjee, Lili Su, Rui Liu, submitted
arXiv: 2409.16577
[C36] Probe-Me-Not: Protecting Pre-trained Encoders from Malicious Probing,
Ruyi Ding†, Tong Zhou†, Lili Su, A. Adam Ding, Xiaolin Xu, and Yunsi Fei,
The Network and Distributed System Security Symposium (NDSS), 2025
[C35] Efficient Federated Learning against Heterogeneous and Non-stationary Client Unavailability,
Ming Xiang†, Stratis Ioannidis, Edmund Yeh, Carlee Joe-Wong, and Lili Su
The Thirty-Eighth Annual Conference on Neural Information Processing Systems (NeurIPS 2024)
3rd place, ACM SIGMETRICS Student Research Competition (SRC) 2024
[C34] Personalized Federated Learning via Feature Distribution Adaptation,
Connor J. McLaughlin and Lili Su
The Thirty-Eighth Annual Conference on Neural Information Processing Systems (NeurIPS 2024)
[C33] Collaborative Learning with Shared Linear Representations: Statistical Rates and Optimal Algorithms,
Xiaochun Niu†, Lili Su, Jiaming Xu, and Pengkun Yang,
NeurIPS Workshop on Federated Foundation Models (oral) (FL@FM-NeurIPS’24), 2024
[C32] On the Convergence Rates of Federated Q-Learning across Heterogeneous Environments,
Muxing Wang†, Pengkun Yang, and Lili Su,
NeurIPS Workshop on Federated Foundation Models (oral) (FL@FM-NeurIPS’24), 2024
[C31] Non-transferable Pruning,
Ruyi Ding†, Lili Su, A. Adam Ding, and Yunsi Fei,
The 18th European Conference on Computer Vision (ECCV), 2024
[C30] Fair Concurrent Training of Multiple Models in Federated Learning,
Marie Siew†, Haoran Zhang†, Jong-Ik Park†, Yuezhou Liu†, Yichen Ruan†, Lili Su, Stratis Ioannidis, Edmund Yeh, and Carlee Joe-Wong,
submitted, 2024
[C29] Network Fault-tolerant and Byzantine-resilient Social Learning via Collaborative Hierarchical Non-Bayesian Learning,
Connor Mclaughlin*, Matthew Ding*, Deniz Erdogmus, and Lili Su,
the 57th Asilomar Conference on Signals, Systems, and Computers (Asilomar 2024)
arXiv: 2307.14952
[C28] Distributed Experimental Design Networks,
Yuanyuan Li†, Lili Su, Carlee Joe-Wong, Edmund Yeh and Stratis Ioannidis,
IEEE International Conference on Computer Communications (IEEE INFOCOM) 2024
2nd place, ACM SIGMETRICS Student Research Competition (SRC) 2023
[C27] pFedLDA: Personalized Federated Learning Through Collaborative Linear Discriminant Analysis,
Connor Mclaughlin†, and Lili Su
International Workshop on Federated Learning in the Age of Foundation Models in Conjunction
with NeurIPS 2023 (FL@FM-NeurIPS 2023)
[C26] Uncertainty-aware Federated Trajectory Prediction via Connected Autonomous Vehicles,
Muzi Peng†, Jiangwei Wang†, Dongjin Song, Fei Miao, and Lili Su
IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2023)
arXiv preprint: arXiv:2303.04340
[C25] (poster) Fair Training of Multiple Federated Learning Models on Resource Con strained Network Devices,
Marie Siew†, Shoba Arunasalam†, Yichen Ruan†, Ziwei Zhu†, Lili Su, Stratis Ioannidis, Edmund Yeh, and Carlee Joe-Wong
2023 ACM/IEEE International Conference on Information Processing in Sensor Networks (IPSN 2023 poster)
Best Poster Award
[C24] Towards Bias Correction of FedAvg over Nonuniform and Time-Varying Communication,
Ming Xiang†, Stratis Ioannidis, Edmund Yeh, Carlee Joe-Wong, and Lili Su,
The 62nd IEEE Conference on Decision and Control (CDC 2023)
[C23] Distributed Non-Convex Optimization with One-Bit Compressors on Heterogeneous Data: Efficient and Resilient Algorithms,
Ming Xiang†, and Lili Su,
submitted, arXiv: 2210.00665
[C22] Cache-Enabled Federated Learning Systems,
Yuezhou Liu†, Lili Su, Carlee Joe-Wong, Stratis Ioannidis, Edmund Yeh, Marie Siew
The 24th International Symposium on Theory, Algorithmic Foundations, and Protocol Design for Mobile Networks and Mobile Computing (MobiHoc 2023), Oct.2023
[C21] Federated Learning in the Presence of Adversarial Client Unavailability,
Ming Xiang, Lili Su, Jiaming Xu, and Pengkun Yang,
submitted, 2023
arXiv preprint arXiv:2305.19971
[C20] Global Convergence of Federated Learning for Mixed Regression,
Lili Su, Jiaming Xu, and Pengkun Yang,
36rd Conference on Neural Information Processing Systems (NeurIPS, 2022), Dec. 2022
[C19] Towards Safe Autonomy in Hybrid Traffic: The Power of Information Sharing in Detecting Abnormal Human Drivers Behaviors,
Jiangwei Wang†, Lili Su, Songyang Han†, Dongjin Song, Fei Miao,
AI4TS workshop at the 31st International Joint Conference On Artificial Intelligence
(AI4TS @ IJCAI 2022), July 2022.
[C18] Experimental Design Networks:A Paradigm for Serving Heterogeneous Learners under Networking Constraints
Yuezhou Liu†, Yuanyuan Li†, Lili Su, Edmund M. Yeh, and Stratis Ioannidis
IEEE INFOCOM, 2022.
[C17] (Invited) Lack of Quorum Sensing Leads to Failure of Consensus in Temnothorax Ant Emigration [link]
Jiajia Zhao†, Lili Su, and Nancy Lynch
Stabilization, Safety, and Security of Distributed Systems (SSS 2021), Nov. 2021.
[C15] On Learning Over-parameterized Neural Networks: A Functional Approximation Perspective [arXiv]
Lili Su and Pengkun Yang
Advances in Neural Information Processing Systems (NeurIPS) 2019, Sept. 2019.
[C14] Securing Distributed Gradient Descent in High Dimensional Statistical Learning [link]
Lili Su and Jiaming Xu
ACM SIGMETRICS 2019, June 2019.
[C13] Collaboratively Learning the Best Option on Graphs, Using Bounded Local Memory [link]
Lili Su*, Martin Zubeldia, and Nancy Lynch
ACM SIGMETRICS 2019
[C12] Distributed Learning with Adversarial Agents Under Relaxed Network Condition [arXiv]
Pooja Vyavahare*, Lili Su, and Nitin H. Vaidya
IEEE Fusion 2019, Jan. 2019.
[C11] On the Convergence Rate of Average Consensus and Distributed Optimization over Unreliable Networks [link]
Lili Su
52nd Asilomar Conference on Signals, Systems, and Computers, Oct. 2018.
[C10] Distributed Statistical Machine Learning in Adversarial Settings: Byzantine Gradient Descent [link]
Yudong Chen, Lili Su*, and Jiaming Xu
ACM SIGMETRICS, 2017
[C9] Ant-Inspired Dynamic Task Allocation via Gossiping [link]
Hsin-Hao Su*, Lili Su, Anna Dornhaus, and Nancy Lynch
Stabilization, Safety, and Security of Distributed Systems (SSS 2017), Nov. 2017.
[C8] Asynchronous Non-Bayesian Learning in the Presence of Crash Failures [link]
Lili Su* and Nitin H.Vaidya
Stabilization, Safety, and Security of Distributed Systems (SSS 2016), Nov. 2016.
[C7] Robust Multi-agent Optimization: Coping with Byzantine Agents with Input Redundancy [link]
Lili Su* and Nitin H.Vaidya
Stabilization, Safety, and Security of Distributed Systems (SSS 2016), Nov. 2016.
[C5] Fault-Tolerant Multi-Agent Optimization: Optimal Iterative Distributed Algorithms [link]
Lili Su and Nitin H.Vaidya
Proceedings of the 2016 ACM Symposium on Principles of Distributed Computing (PODC 2016), July 2016.
[C4] Multi-agent optimization in the presence of Byzantine adversaries: Fundamental limits [link]
Lili Su and Nitin H.Vaidya
IEEE American Control Conference (ACC 2016), July 2016.