|
Liekang Zeng Postdoctoral Research Fellow Embedded AI and IoT Lab Department of Information Engineering The Chinese University of Hong Kong E-mail: lkzeng [AT] cuhk [dot] edu [dot] hk My GitHub, dblp, and Google Scholar [>3000 citations] |
|
Biography
I am currently a postdoctoral research fellow at The Chinese University of Hong Kong, working with Prof. Guoliang Xing. I obtained my Ph.D. degree (with honor), under the supervision of Prof. Xu Chen, and B.E. degree (with honor) at Sun Yat-sen University.
Research Interests
My research interest lies in building full-stack edge intelligence systems with real-time responsiveness, systematic resource efficiency, and theoretical performance guarantee.
Currently, I focus on developing efficient and affordable LLM and graph learning systems with distributed edge computing.
Research Overview:
- Collaborative Edge Intelligence 🌟[project page]
- Generative language models: Perspecitve [WCM'24], Asteroid [MobiCom'24], Galaxy [INFOCOM'24], PAC [ICPP'24]
- Graph neural networks: Fograph+ [TON'23], GLAD [JSAC'22], Fograph [WWW'22]
- Convolutional vision models: Eco-FL [ICPP'22], CoEdge [TON'21], Edgent [TWC'20], Boomerang [NET'19]
- Definition and taxonomy of edge intelligence: Edge Graph Intelligence [Preprint], Edge AI [PIEEE'19]
- Edge Robotics
- Edge Network Optimization
News
- ⬆️ Our project homepage of Collaborative Edge Intelligence has been officially launched. Check it out!
- [Dec. 2024] Two papers on LLM computation scheduling and generative model serving in collaborative edge networks are accepted to INFOCOM'24. Congrats, Mulei and Shengyuan!
- [Nov. 2024] Present our edge collaborative training work Asteroid at MobiCom 2024.
- [Oct. 2024] Our work on edge resource probing and exploitation is accepted by TSC.
- [Oct. 2024] Our work on privacy budget reuse in Federated Learning is accepted by TMC. Congrats, Jingyi!
- [Aug. 2024] Invited to serve as a TPC member in MSN'24 and NPC'24.
- [July 2024] Our survey on edge graph intelligence is released at Arxiv.
- [June 2024] Our work on online utility optimization in collaborative edge network is accepted by TON.
- [June 2024] Our work on edge-enabled LLM fine-tuning is accepted by ICPP. Congrats, Bei and Shengyuan!
- [May 2024] Our work on data heterogeneity resilient federated learning is accepted by JSAC. Congrats, Mulei!
- [Apr. 2024] Our work on the vision of collaborative edge computing for LLMs is accepted by IEEE Wireless Communications.
- [Apr. 2024] Our work on energy-efficient federated learning is accepted by IEEE Internet of Things Magazine. Congrats, Chenyu!
- [Apr. 2024] Awarded as the Excellent Reviewer of IEEE TNSE by IEEE Communications Society. ...
Selected Publications
Full Publications, * indicates equal contribution, # indicates corresponding author, + indicates the student mentored by me.
- Multi-tier Multi-node Scheduling of LLM for Collaborative AI Computing.
[paper] [bibtex]
Mulei Ma+, Chenyu Gong+, Liekang Zeng#, Yang Yang.
IEEE International Conference on Computer Communications (INFOCOM), 2025. CCF-A. - Jupiter: Fast and Resource-Efficient Collaborative Inference of Generative LLMs on Edge Devices.
[paper] [bibtex]
Shengyuan Ye+, Bei Ouyang, Liekang Zeng, Tianyi Qian, Xiaowen Chu, Jian Tang, Xu Chen.
IEEE International Conference on Computer Communications (INFOCOM), 2025. CCF-A. - Implementation of Big AI Models for Wireless Networks with Collaborative Edge Computing.
[paper] [bibtex]
Liekang Zeng, Shengyuan Ye+, Xu Chen, Yang Yang.
IEEE Wireless Communications, 2024. - FlocOff: Data Heterogeneity Resilient Federated Learning with Communication-Efficient Edge Offloading.
[paper] [bibtex]
Mulei Ma+, Chenyu Gong+, Liekang Zeng#, Yang Yang, Liantao Wu.
IEEE Journal of Selected Areas in Communications (JSAC), 2024. CCF-A. - Asteroid: Resource-Efficient Hybrid Pipeline Parallelism for Collaborative DNN Training on Heterogeneous Edge Devices.
[paper] [bibtex] [slides]
Shengyuan Ye*+, Liekang Zeng*, Xiaowen Chu, Guoliang Xing, Xu Chen.
ACM International Conference on Mobile Computing and Networking (MobiCom), 2024. CCF-A. - A3D: Adaptive, Accurate and Autonomous Navigation for Edge-Assisted Drones.
[paper] [bibtex]
Liekang Zeng, Haowei Chen+, Daipeng Feng+, Xiaoxi Zhang, Xu Chen.
IEEE/ACM Transactions on Networking (TON), 2023. CCF-A. - Serving Graph Neural Networks with Distributed Fog Servers for Smart IoT Services.
[paper] [bibtex]
Liekang Zeng, Xu Chen, Peng Huang+, Ke Luo, Xiaoxi Zhang, Zhi Zhou.
IEEE/ACM Transactions on Networking (TON), 2023. CCF-A. - GNN at the Edge: Cost-Efficient Graph Neural Network Processing over Distributed Edge Servers.
[paper] [bibtex] [blog]
Liekang Zeng, Chongyu Yang+, Peng Huang+, Zhi Zhou, Shuai Yu, Xu Chen.
IEEE Journal of Selected Areas in Communications (JSAC), 2022. CCF-A. - Fograph: Enabling Real-Time Deep Graph Inference with Fog Computing.
[paper] [slides] [video] [bibtex] [blog]
Liekang Zeng, Peng Huang+, Ke Luo, Xiaoxi Zhang, Zhi Zhou, Xu Chen.
The Web Conference (WWW), 2022. CCF-A, AR=17.7%. - CoEdge: Cooperative DNN Inference with Adaptive Workload Partitioning over Heterogeneous Edge Devices.
[paper] [bibtex]
Liekang Zeng, Xu Chen, Zhi Zhou, Lei Yang, Junshan Zhang.
IEEE/ACM Transactions on Networking (TON), 2021. CCF-A.
🏵️ Recognized in TON's Top 5 popular articles (Dec. 2021 - Oct. 2022). - Edge AI: On-Demand Accelerating Deep Neural Network Inference via Edge Computing.
[paper] [bibtex] [press-ABI Research]
En Li*, Liekang Zeng*, Zhi Zhou, Xu Chen.
IEEE Transactions on Wireless Communications (TWC), 2020. CCF-B.
🔥 ESI Highly Cited Paper (700+ Citations). - Boomerang: On-Demand Cooperative Deep Neural Network Inference for Edge Intelligence on the Industrial Internet of Things.
[paper] [bibtex] [press-ABI Research]
Liekang Zeng, En Li, Zhi Zhou, Xu Chen.
IEEE Network (NET), 2019. - Edge Intelligence: Paving the Last Mile of Artificial Intelligence with Edge Computing.
[paper] [bibtex] [book] [press-APNet] [press-IEEE]
Zhi Zhou, Xu Chen, En Li, Liekang Zeng, Ke Luo, Junshan Zhang.
Proceedings of the IEEE (PIEEE), 2019. CCF-A.
🔥 ESI Highly Cited Paper (2000+ Citations).
Selected Awards
- Excellent Reviewer for IEEE Transactions on Network Science and Engineering, 2024
- SYSU Outstanding Ph.D. Graduate (Summa Cum Laude), 2023
- SYSU Presidential Fellowship, 2022
- National Ph.D. Scholarship, 2022
- Professor Shu-Jun Wang Memorial Fellowship, 2021
- Excellent Ph.D. Student Scholarship, 2018-2023
- SYSU Outstanding Undergraduate (Summa Cum Laude), 2018
- Finalist Award, Mathematical Contest in Modeling/Interdisciplinary Contest in Modeling, 2016
- Excellent Undergraduate Student Scholarship, 2014-2018
Working Experience
- Research assistant at National Supercomputing Center in Guangzhou (Spring 2018)
- Research intern at Cloud & Mobile Research Group, Microsoft Research Asia (Fall 2017)
Teaching Experience
- DCS6270: Edge Computing. (Spring 2022)
- DCS207: Principles of Computer Organization. (Fall 2021)
- EIT116/EIT118: Digital Circuits and Logical Design. (Spring 2020, Spring 2019)
- DCS110/DCS112: Object-Oriented Programming. (Spring 2019, Spring 2017)
Academic Services
-
Program Committee Member
- International Conference on Mobility, Sensing and Networking 2024, 2023
- IFIP International Conference on Network and Parallel Computing 2024
- International Workshop on Intelligent Cloud Computing and Networking 2022, 2021 (Co-located with INFOCOM 2022, 2021)
- International Workshop on Mobility in the Evolving Internet Architecture 2019 (Co-located with ICNP 2019)
-
Journal Reviewer
- IEEE/ACM Transactions on Networking
- IEEE Journal of Selected Areas in Communications
- IEEE Transactions on Mobile Computing
- IEEE Transactions on Parallel and Distributed Systems
- IEEE Transactions on Computers
- IEEE Transactions on Wireless Communications
- IEEE Transactions on Network Science and Engineering
- IEEE Internet of Things Journal
- IEEE Transactions on Vehicular Technology
- ACM Transactions on Internet Technology
- ACM Transactions on Autonomous and Adaptive Systems
- ACM Transactions on Computing for Healthcare