Ph.D. Student in Electrical Engineering
University of Southern California
Los Angeles, USA
tuozhang [at] usc.edu
Tuo Zhang is a Ph.D. student in the EE department at the University of Southern California. Currently, he is advised by Prof. Salman Avestimehr. Before joining USC, he received his Bachelor of Science with High Honor from the University of California, Santa Barbara under the supervision of Prof. Mahnoosh Alizadeh and Prof. Forrest Brewer. His research now focuses on distributed/federated machine learning algorithms, systems, and applications.
Publications
- [10] FedAIoT: A Federated Learning Benchmark for Artificial Intelligence of Things
Samiul Alam, Tuo Zhang, Tiantian Feng, Hui Shen, Zhichao Cao, Dong Zhao, JeongGil Ko, Kiran Somasundaram, Shrikanth Narayanan, Salman Avestimehr, Mi Zhang
Under Review
[Arxiv] [Github]
TL; DR: Unified framework for benchmarking federated learning in AIoT, providing diverse datasets, tasks and analyses.
- [9] GPT-FL: Generative Pre-trained Model-Assisted Federated Learning
Tuo Zhang*, Tiantian Feng*, Samiul Alam, Dimitrios Dimitriadis, Mi Zhang, Shrikanth Narayanan, Salman Avestimehr (* means co-1st authors)
Under Review
[Arxiv]
TL; DR: A novel Federated Learning format that leverages generative pre-trained models on the server side. - [8] FedMultimodal: A Benchmark for Multimodal Federated Learning
Tiantian Feng, Digbalay Bose, Tuo Zhang, Rajat Hebbar, Anil Ramakrishna, Rahul Gupta, Mi Zhang, Salman Avestimehr, Shrikanth Narayanan
KDD 2023 – 29th ACM SIGKDD Conference
[Arxiv] [Github]
TL; DR: A benchmark for multimodal Federated Learning. - [7] TimelyFL: Heterogeneity-aware Asynchronous Federated Learning with Adaptive Partial Training
Tuo Zhang, Lei Gao, Sunwoo Lee, Mi Zhang, Salman Avestimehr
CVPR 2023 FedVision (Oral)
[Proceeding] [Arxiv]
TL; DR: An inclusiveness asynchronous federated learning with adaptive partial training.
- [6] Secure Federated Learning against Model Poisoning Attacks via Client Filtering
Duygu Nur Yaldiz*, Tuo Zhang*, Salman Avestimehr (* means co-1st authors)
ICLR 2023 Workshop on Backdoor Attacks and Defenses in Machine Learning (BANDS)
[Arxiv] [Github]
TL; DR: A cosine-similarity-based attacker detection algorithm against model poisoning attacks under FL framework.
- [5] FedAudio: A Federated Learning Benchmark for Audio Tasks
Tuo Zhang*, Tiantian Feng*, Samiul Alam, Sunwoo Lee, Mi Zhang, Shrikanth S. Narayanan, Salman Avestimehr (* means co-1st authors)
ICASSP 2023 – 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
[Proceeding] [Arxiv] [Github]
TL; DR: The first benchmark paper for FL plus audio with both clean and noisy data.
- [4] Federated Learning for Internet of Things: Applications, Challenges, and Opportunities
Tuo Zhang, Lei Gao, Chaoyang He, Mi Zhang, Bhaskar Krishnamachari, Salman Avestimehr
IEEE Internet of Things Magazine (IEEE IoTM), March 2022
[Proceeding] [Arxiv]
TL; DR: A very good introduction paper for federated learning
- [3] Layer-wise Adaptive Model Aggregation for Scalable Federated Learning
Sunwoo Lee, Tuo Zhang, Salman Avestimehr
AAAI 2023 – Thirty-Seventh AAAI Conference on Artificial Intelligence
[Proceeding] [Arxiv]
TL; DR: Layer-wise adaptive model aggregation scheme for communication-efficient Federated Learning.
- [2] Federated Learning for Internet of Things: A Federated Learning Framework for On-device Anomaly Data Detection
Tuo Zhang*, Chaoyang He*, Tianhao Ma, Lei Gao, Mark Ma, Salman Avestimehr (* means co-1st authors)
ACM Embedded Networked Sensor Systems SenSys 2021 (AIChallengeIoT)
[Proceeding] [Arxiv] [GitHub]
TL; DR: IoT x Federated Learning
- [1] Mobility-Aware Smart Charging of Electric Bus Fleets
A Moradipari, N Tucker, T Zhang, G Cezar, M Alizadeh
2020 IEEE Power & Energy Society General Meeting (PESGM)
[Proceeding] [Arxiv]
Recent News
- 05/17/2023: Our paper, FedMultimodal: A Benchmark for Multimodal Federated Learning, has been accepted to KDD 2023. Please have a look at our code and paper!
- 03/31/2023: Our paper, TimelyFL: Heterogeneity-aware Asynchronous Federated Learning with Adaptive Partial Training, has been accepted to CVPR 2023 (FedVision). See you in Vancouver! 🏙️
- 03/04/2023: Our paper, Secure Federated Learning against Model Poisoning Attacks via Client Filtering, has been accepted to ICLR BANDS 2023.
- 02/15/2023: Our paper, FedAudio: A Federated Learning Benchmark for Audio Tasks, has been accepted to ICASSP 2023. See you in Greece! 🇬🇷
- 11/19/2022: Our paper, Layer-wise adaptive model aggregation for scalable federated learning, has been accepted to AAAI 2023. See you in DC! 🏛️
- 10/30/2022: We have released the FedAudio, the first federated learning benchmark dataset for audio tasks!
- 03/04/2022: Our FL + IoT Survey paper has been accepted to IEEE Internet of Things Magazine (IEEE IoTM), March 2022 Special Issue: An End-to-end Machine Learning Perspective on Industrial IoT
- 10/20/2021: Our FedIoT paper has been admitted to accepted to ACM Embedded Networked Sensor Systems SenSys 2021 (AIChallengeIoT)
- 08/01/2020: Joined USC as a Ph.D. student in the summer
- 06/15/2020: Graduated from UCSB with a B.S. with High Honor
Professional Activities
- Journal Reviews
- IEEE Journal on Selected Areas in Communications (IEEE J-SAC)
(1 Review) - IEEE Transactions on Mobile Computing (2 Review)
- IEEE Transactions on Parallel and Distributed Systems (1 Review)
- Journal of Software: Practice and Experience (1 Review)
- IEEE Internet of Things Magazine (1 Review)
- IEEE Internet of Things Journal (1 Review)
- IEEE Communication Magazine (1 Review)
- Journal of Software: Practice and Experience (1 Review)
- The Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies
(1 Review) - IEEE Transactions on Neural Networks and Learning Systems (1 Review)
- IEEE/ACM Transactions on Networking (2 Review)
- IEEE Journal on Selected Areas in Communications (IEEE J-SAC)
- Conference Reviews
- ICML 2022 (2 Review)
- NeurIPS 2022 (5 Review)
- AAAI 2023 (6 Review)
- AISTATS 2023 (4 Review)
- ICML 2023 (6 Review)
- NeurIPS 2023 (6 Review)
- AAAI 2024 (3 Review)
- ICLR 2024 (4 Review)
- ICASSP 2024 (2 Review)
- ICML 2024 (3 Review)
- CVPR FedVision 2024 (1 Review)
- Book Series Proposal Reviews
- Springer Nature Computer Science