Ziqing Fan
- Locally Estimated Global Perturbations are Better than Local Perturbations for Federated Sharpness-aware Minimization
2024/05/29 by Ziqing Fan, Shengchao Hu, Fan, Ziqing +11 · 7 citations
Computer Science · Engineering · #Distributed #FOS: Computer and information sciences #Ferroelectric and Negative Capacitance Devices #Machine Learning (cs.LG) #Parallel #Privacy-Preserving Technologies in Data #Stochastic Gradient Optimization Techniques #and Cluster Computing (cs.DC)
- Q-value Regularized Transformer for Offline Reinforcement Learning
2024/05/27 by Shengchao Hu, Hu, Shengchao, Ziqing Fan +11 · 5 citations
Engineering · Computer Science · #Elevator Systems and Control #Iterative Learning Control Systems #Adaptive Dynamic Programming Control
- Fourier-based augmentation with applications to domain generalization
2023/03/01 by Qinwei Xu, Ruipeng Zhang, Ziqing Fan +4 · 3 citations
Computer Science · #Domain Adaptation and Few-Shot Learning #Multimodal Machine Learning Applications #Music and Audio Processing
- Reconstruct the Pruned Model without Any Retraining
2024/07/18 by Pingjie Wang, Ziqing Fan, Wang, Pingjie +9 · 2 citations
Computer Science · #Natural Language Processing Techniques #Topic Modeling #Speech Recognition and Synthesis
- Federated Learning under Partially Class-Disjoint Data via Manifold Reshaping
2024/05/29 by Ziqing Fan, Jiangchao Yao, Fan, Ziqing +9 · 1 citation
Computer Science · #Distributed #FOS: Computer and information sciences #Machine Learning (cs.LG) #Parallel #Privacy-Preserving Technologies in Data #Stochastic Gradient Optimization Techniques #and Cluster Computing (cs.DC)
- Continual Task Learning through Adaptive Policy Self-Composition
2024/11/18 by Shengchao Hu, Hu, Shengchao, Yuhang Zhou +11 · 1 citation
Computer Science · Decision Sciences · Social Sciences · #Artificial Intelligence (cs.AI) #Context-Aware Activity Recognition Systems #FOS: Computer and information sciences #Knowledge Management and Sharing #Machine Learning (cs.LG) #Personal Information Management and User Behavior