Dongrun Li — accepted AI-conference papers

2026

Eliminating Solution Bias in Differentially Private Optimization

DONGRUN LI, YUN ZENG, Zibo Wei, Jiacheng Wei, Qinnan Zhang, Faguo Wu +2

ICML 2026poster

Differentially private (DP) stochastic optimization algorithms are widely used in privacy-preserving deep learning, where per-sample gradient clipping and noise injection protect sensitive information. However, these operations limit existing DP algorithms to converge within a constant-radius neighb…

Cited by 0 Source ↗Scholar ↗

2025

FedSaaS: Class-Consistency Federated Semantic Segmentation via Global Prototype Supervision and Local Adversarial Harmonization

Xiaoyang Yu, Xiaoming Wu, Xin Wang, Dongrun Li, Ming Yang, Peng Cheng

IJCAI 2025

Federated semantic segmentation enables pixel-level classification in images through collaborative learning while maintaining data privacy. However, existing research commonly overlooks the fine-grained class relationships within the semantic space when addressing heterogeneous problems, particularl

Cited by 0 Source ↗PDF ↗Scholar ↗