Selected Recent Publications
- F. Wu, J. Hu, G. Min, S. Wang, “Efficient orthogonal fine-tuning with principal subspace adaptation” , in International Conference on Learning Representations (ICLR), Apr. 2026.
- H. Woisetschlager, R. Zhang, S. Wang, H.-A. Jacobsen, “MESS+: dynamically learned inference-time LLM routing in model zoos with service level guarantees” , in Annual Conference on Neural Information Processing Systems (NeurIPS), Dec. 2025 (acceptance rate: 24.5%).
- A. Piaseczny, M. K. C. Shisher, S. Wang, C. Brinton, “RCCDA: adaptive model updates in the presence of concept drift under a constrained resource budget” , in Annual Conference on Neural Information Processing Systems (NeurIPS), Dec. 2025 (acceptance rate: 24.5%).
- R. Zhu, M. Yang, S. Wang, J. Yang, Q. Wang, “Flick: empowering federated learning with commonsense knowledge” , in Annual Conference on Neural Information Processing Systems (NeurIPS), Dec. 2025 (acceptance rate: 24.5%).
- L. Yuan, D.-J. Han, S. Wang, C. Brinton, “Local-Cloud Inference Offloading for LLMs in Multi-Modal, Multi-Task, Multi-Dialogue Settings” , in ACM International Symposium on Theory, Algorithmic Foundations, and Protocol Design for Mobile Networks and Mobile Computing (MobiHoc), Oct. 2025 (best paper runner-up, top 3 of 169 submissions, overall acceptance rate: 23.1%).
- D. Sow, H. Woisetschlager, S. Bulusu, S. Wang, H.-A. Jacobsen, Y. Liang, “Dynamic loss-based sample reweighting for improved large language model pretraining” , in International Conference on Learning Representations (ICLR), May 2025.
- P. Valdeira, S. Wang, Y. Chi, “Vertical federated learning with missing features during training and inference” , in International Conference on Learning Representations (ICLR), May 2025.
- W. Fang, D.-J. Han, E. Chen, S. Wang, C. Brinton, “Hierarchical federated learning with multi-timescale gradient correction” , in the 38th Conference on Neural Information Processing Systems (NeurIPS), Dec. 2024 (acceptance rate: 25.8%).
- H. Woisetschlager, A. Erben, R. Mayer, S. Wang, H.-A. Jacobsen, “FLEdge: benchmarking federated machine learning applications in edge computing systems” , in ACM/IFIP International Middleware Conference (MIDDLEWARE), Dec. 2024. [DOI] [Code]
- H. Woisetschlager, A. Erben, B. Marino, S. Wang, N. D. Lane, R. Mayer, H.-A. Jacobsen, “Federated learning priorities under the European Union Artificial Intelligence Act” , in Workshop on Generative AI and Law (GenLaw) in Conjunction with ICML 2024, Jul. 2024.
- S. Wang, M. Ji, “A lightweight method for tackling unknown participation statistics in federated averaging” , in International Conference on Learning Representations (ICLR), May 2024 (spotlight, 5% of submitted papers). [Proceedings Link] [Code]
- D. Jhunjhunwala, S. Wang, G. Joshi, “FedFisher: leveraging Fisher information for one-shot federated learning” , in International Conference on Artificial Intelligence and Statistics (AISTATS), May 2024. [Proceedings Link] [Code]
- Y. Jiang, S. Wang, V. Valls, B. J. Ko, W.-H. Lee, K. K. Leung, L. Tassiulas, “Model pruning enables efficient federated learning on edge devices” , IEEE Transactions on Neural Networks and Learning Systems, vol. 34, no. 12, pp. 10374 - 10386, Dec. 2023. [DOI] [Code]
- D. Jhunjhunwala, S. Wang, G. Joshi, “FedExP: speeding up federated averaging via extrapolation” , in International Conference on Learning Representations (ICLR), May 2023 (spotlight - notable-top-25%, top 25% of accepted papers, approximately top 8% of submitted papers). [Proceedings Link] [Code]
- S. Wang, J. Perazzone, M. Ji, K. Chan, “Federated learning with flexible control” , in IEEE International Conference on Computer Communications (INFOCOM), May 2023 (acceptance rate: 19.2%). [DOI] [Code]
- S. Wang, M. Ji, “A unified analysis of federated learning with arbitrary client participation” , in the 36th Conference on Neural Information Processing Systems (NeurIPS), Nov.-Dec. 2022 (acceptance rate: 25.6%). [Proceedings Link] [Code]
- A. Feng, C. You, S. Wang, L. Tassiulas, “KerGNNs: interpretable graph neural networks with graph kernels” , in AAAI Conference on Artificial Intelligence, Feb.-Mar. 2022 (oral presentation, oral acceptance rate: 4.6%, overall acceptance rate: 15.0%). [DOI] [Code]
- S. Wang, T. Tuor, T. Salonidis, K. K. Leung, C. Makaya, T. He, K. Chan, “Adaptive federated learning in resource constrained edge computing systems” , IEEE Journal on Selected Areas in Communications, vol. 37, no. 6, pp. 1205 - 1221, Jun. 2019 (acceptance rate of this special issue of the journal: 13%, received the IEEE Communications Society Leonard G. Abraham Prize in 2021). [DOI] [Code]
For the full publication list, visit shiqiang.wang/#publications .