I am a Ph.D. student at Friedrich-Alexander-Universität Erlangen-Nürnberg (FAU), where I work at the Chair for Dynamics, Control, Machine Learning and Numerics–Alexander von Humboldt Professorship, under the supervision of Prof. Enrique Zuazua.

Research Interests

I am particularly interested in Federated Learning from a multi-level perspective: 1) server-side fair and robust aggregation; 2) client-side drift control and local optimization; 3) system-level game-theoretic incentives; and 4) privacy risks in distributed training.

Selected Publications

^* Alphabetical authorship according to mathematical tradition, corresponding author.

• Kang Liu, Ziqi Wang^*, and Enrique Zuazua, “Nonlinear Equilibrium Transitions in a Potential Game Model for Federated Learning,” Physica D: Nonlinear Phenomena, 2026.
• Yongcun Song, Ziqi Wang^*, and Enrique Zuazua, “Approximate and Weighted Data Reconstruction Attack in Federated Learning,” IEEE Transactions on Big Data, 2026.
• Yongcun Song, Ziqi Wang^*, and Enrique Zuazua, “FedADMM-InSa: An Inexact and Self-Adaptive ADMM for Federated Learning,” Neural Networks, 2025.

See the research page for the full list.