My name is Yiyue Chen (陈祎玥) and I am currently a final-year PhD student at The University of Texas at Austin. My academic track is Decision, Information, and Communications Engineering (DICE) in Electrical and Computer Engineering department and I am part of the Wireless Networking and Communications Group (WNCG). I am fortunate to be supervised by Dr. Haris Vikalo. I received my MSE degree in Electrical and Computer Engineering deparment at UT Austin in 2020 and BS degree in Applied Mathematics from Wuhan University in 2018.

Research Interests

My research interests include distributed optimization, large-scale machine learning and self-supervised learning under resource constraints. I am passionate about developing and understanding machine learning/deep learning algorithms for real world challenges. In particular, my focus is on learning over dynamic networks and heterogeneous-resource agents. When the network is directed and time-varying, I have designed, implemented and analyzed efficient distributed optimization algorithms. In dealing with the resource-heterogeneous clients, I have proposed a unique algorithm that can address multiple resource heterogeneities with both theoretical and experimental demonstration. Moreover, I have extensive industry experience on researching and establishing AI-based solutions to practical problems.

Publications

• Fed-QSSL: A Framework for Personalized Federated Learning under Bitwidth and Data Heterogeneity, the 38th AAAI Conference on Artificial Intelligence (AAAI-24)
• Accelerated Distributed Stochastic Non-Convex Optimization over Time-Varying Directed Networks
  ICASSP 2023-2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
• Communication-efficient variance-reduced decentralized stochastic optimization over time-varying directed graphs
  IEEE Transactions on Automatic Control 67 (12), 6583-6594
• Decentralized optimization on time-varying directed graphs under communication constraints
  ICASSP 2021-2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
• Federated Learning with Infrastructure Resource Limitations in Vehicular Object Detection
  2021 IEEE/ACM Symposium on Edge Computing (SEC)