Yujia Wang

About

I am a Tenure-Track Assistant Professor in the School of Computing at DePaul University, which I joined in Fall 2026. I received my Ph.D. in the College of Information Sciences and Technology, Penn State University, advised by Jinghui Chen. Previously, I obtained my M.S. in Applied Statistics in the Department of Statistics at the University of Michigan, and my B.S. in Statistics in the College of Mathematics at Sichuan University.

I aim to build the next generation of collaborative intelligence systems and I seek to establish the foundational infrastructure for collaborative learning through advanced optimization theory. My current research focuses on the theoretical foundations and practical methodologies of collaborative and privacy-preserving machine learning and optimization, including:

• Efficient and scalable federated learning in heterogeneous networks
• Generative methodologies in federated and collaborative learning
• Optimization methods tailored for the era of generative AI

I look forward to connecting with prospective Ph.D. students, research interns, and researchers who are interested in exploring research ideas and opportunities together at DePaul. If you would like to work with me, please email me at yujiawa98@gmail.com with your CV and a brief introduction to your research interests.

News

Publications

Submitted Papers

1. Stragglers Can Contribute More: Uncertainty-Aware Distillation for Asynchronous Federated Learning
   Yujia Wang, Fenglong Ma, and Jinghui Chen
   Submitted.

Conference and Journal Publications

1. Federated Learning with Projected Trajectory Regularization
   Tiejin Chen*, Yuanpu Cao*, Yujia Wang*, Cho-Jui Hsieh, and Jinghui Chen
   To appear in Transactions on Machine Learning Research (TMLR), 2026.
2. ParaBlock: Communication-Computation Parallel Block Coordinate Federated Learning for Large Language Models
   Yujia Wang, Yuanpu Cao, and Jinghui Chen
   In Transactions on Machine Learning Research (TMLR), 2026.
   paper
3. AltLoRA: Towards Better Gradient Approximation in Low-Rank Adaptation with Alternating Projections
   Xin Yu, Yujia Wang, Jinghui Chen, and Lingzhou Xue
   In Proceedings of the 39th Annual Conference on Neural Information Processing Systems (NeurIPS), 2025.
   paper
4. JOPA: Explaining Large Language Model's Generation via Joint Prompt Attribution
   Yurui Chang*, Bochuan Cao*, Yujia Wang, Jinghui Chen, and Lu Lin
   In the 63rd Annual Meeting of the Association for Computational Linguistics (ACL Main), 2025.
   paper
5. On the Data Heterogeneity in Adaptive Federated Learning
   Yujia Wang, and Jinghui Chen
   In Transactions on Machine Learning Research (TMLR), 2024.
   paper
6. FADAS: Towards Federated Adaptive Asynchronous Optimization
   Yujia Wang, Shiqiang Wang, Songtao Lu, and Jinghui Chen
   In Proceedings of the 41st International Conference on Machine Learning (ICML), 2024.
   paper
7. Tackling the Data Heterogeneity in Asynchronous Federated Learning with Cached Update Calibration
   Yujia Wang, Yuanpu Cao, Jingcheng Wu, Ruoyu Chen, and Jinghui Chen
   In Proceedings of the 12th International Conference on Learning Representations (ICLR), 2024.
   paper
8. Communication-Efficient Adaptive Federated Learning
   Yujia Wang, Lu Lin, and Jinghui Chen
   In Proceedings of the 39th International Conference on Machine Learning (ICML), 2022.
   paper
9. Communication-Compressed Adaptive Gradient Method for Distributed Nonconvex Optimization
   Yujia Wang, Lu Lin, and Jinghui Chen
   In Proceedings of the 25th International Conference on Artificial Intelligence and Statistics (AISTATS), 2022.
   paper

Workshop Papers & Doctoral Forum

1. Towards Efficient Federated Learning in Heterogeneous Networks
   Yujia Wang
   In SIAM International Conference on Data Mining (SDM Doctoral Forum), 2024.
   
2. Accelerating Adaptive Federated Optimization with Local Gossip Communications
   Yujia Wang, Pei Fang, and Jinghui Chen
   International Workshop on Federated Learning: Recent Advances and New Challenges, NeurIPS 2022.
   

Experiences

Awards & Honors

Services