Ang Li

I am currently a tenure-track assistant professor in the Department of Electrical and Computer Engineering at University of Maryland College Park. Before joining UMD, I was a Research Associate in Qualcomm AI Research. I obtained Ph.D. from Duke University under the supervision of Professor Yiran Chen. My research interests lie in the intersection of machine learning and edge computing, with a focus on building large-scale networked and trustworthy intelligent systems to solve practical problems in a collaborative, scalable, secure, and ubiquitous manner.

Openings: I’m looking for highly motivated Ph.D., master students, and research interns to join my group. If you are interested, please send an email to angliece@umd.edu with you CV and transcripts attached.

News

02/26/2024	Our research paper titled “MAPSeg: Unified Unsupervised Domain Adaptation for Heterogeneous Medical Image Segmentation Based on 3D Masked Autoencoding and Pseudo-Labeling” has been accepted by CVPR 2024.
02/24/2024	Our research paper titled “SiDA: Sparsity-Inspired Data-Aware Serving for Efficient and Scalable Large Mixture-of-Experts Models” has been accepted by MLSys 2024.
01/22/2024	Our research paper titled “FedHyper: A Universal and Robust Learning Rate Scheduler for Federated Learning with Hypergradient Descent” and “Enhancing One-Shot Federated Learning Through Data and Ensemble Co-Boosting” have been accepted by ICLR 2024.
10/07/2023	Our research paper titled “FedNAR: Federated Optimization with Normalized Annealing Regularization” has been accepted by NeurIPS 2023.
08/14/2023	I am deeply honored and thrilled to share that I have been selected as the recipient of the IEEE Cyber-Physical Systems (TCCPS) Outstanding Ph.D. Dissertation Award!
05/08/2023	I am beyond thrilled to share that I have been selected as one of the two recipients for the ECE Department Outstanding Ph.D. Dissertation Award for the academic year 22-23 at Duke University!
04/27/2023	Our research paper titled “Fed-CBS: A Heterogeneity-Aware Client Sampling Mechanism for Federated Learning via Class-Imbalance Reduction” has been accepted for presentation at ICML 2023.
04/25/2023	I am beyond thrilled to share that I have been selected as one of the two recipients for the ECE Department Outstanding Ph.D. Dissertation Award for the academic year 22-23 at Duke University!
03/15/2023	Our paper “AutoFed: Heterogeneity-Aware Federated Multimodal Learning for Robust Autonomous Driving” has been accepted by MobiCom 2023!
10/10/2022	Our paper “FedSEA: A Semi-Asynchronous Federated Learning Framework for Extremely Heterogeneous Devices” has been accepted by SenSys 2022!

Selected Publications

SEC

LotteryFL: empower edge intelligence with personalized and communication-efficient federated learning

Ang Li, Jingwei Sun, Binghui Wang, and 4 more authors

In 2021 IEEE/ACM Symposium on Edge Computing (SEC), 2021

arXiv Bib HTML Code

@inproceedings{li2021lotteryfl,
  title = {LotteryFL: empower edge intelligence with personalized and communication-efficient federated learning},
  author = {Li, Ang and Sun, Jingwei and Wang, Binghui and Duan, Lin and Li, Sicheng and Chen, Yiran and Li, Hai},
  booktitle = {2021 IEEE/ACM Symposium on Edge Computing (SEC)},
  pages = {68--79},
  year = {2021},
  organization = {IEEE},
}

KDD

TIPRDC: task-independent privacy-respecting data crowdsourcing framework for deep learning with anonymized intermediate representations

Ang Li, Yixiao Duan, Huanrui Yang, and 2 more authors

In Proceedings of the 26th ACM SIGKDD international conference on knowledge discovery & data mining, 2020

Bib PDF Code

@inproceedings{li2020tiprdc,
  title = {TIPRDC: task-independent privacy-respecting data crowdsourcing framework for deep learning with anonymized intermediate representations},
  author = {Li, Ang and Duan, Yixiao and Yang, Huanrui and Chen, Yiran and Yang, Jianlei},
  booktitle = {Proceedings of the 26th ACM SIGKDD international conference on knowledge discovery \& data mining},
  pages = {824--832},
  year = {2020},
}

MobiCom

Hermes: an efficient federated learning framework for heterogeneous mobile clients

Ang Li, Jingwei Sun, Pengcheng Li, and 3 more authors

In Proceedings of the 27th Annual International Conference on Mobile Computing and Networking, 2021

Bib PDF

@inproceedings{li2021hermes,
  title = {Hermes: an efficient federated learning framework for heterogeneous mobile clients},
  author = {Li, Ang and Sun, Jingwei and Li, Pengcheng and Pu, Yu and Li, Hai and Chen, Yiran},
  booktitle = {Proceedings of the 27th Annual International Conference on Mobile Computing and Networking},
  pages = {420--437},
  year = {2021},
}

SenSys

Fedmask: Joint computation and communication-efficient personalized federated learning via heterogeneous masking

Ang Li, Jingwei Sun, Xiao Zeng, and 3 more authors

In Proceedings of the 19th ACM Conference on Embedded Networked Sensor Systems, 2021

Bib HTML PDF

@inproceedings{li2021fedmask,
  title = {Fedmask: Joint computation and communication-efficient personalized federated learning via heterogeneous masking},
  author = {Li, Ang and Sun, Jingwei and Zeng, Xiao and Zhang, Mi and Li, Hai and Chen, Yiran},
  booktitle = {Proceedings of the 19th ACM Conference on Embedded Networked Sensor Systems},
  pages = {42--55},
  year = {2021},
}