collaborators

10 papers

cs.LG2026

FedBCD:Communication-Efficient Accelerated Block Coordinate Gradient Descent for Federated Learning

Junkang Liu, Fanhua Shang, Yuanyuan Liu +3

Although Federated Learning has been widely studied in recent years, there are still high overhead expenses in each communication round for large-scale models such as Vision Transf…

cs.LG2026

FedNSAM:Consistency of Local and Global Flatness for Federated Learning

Junkang Liu, Fanhua Shang, Yuxuan Tian +2

In federated learning (FL), multi-step local updates and data heterogeneity usually lead to sharper global minima, which degrades the performance of the global model. Popular FL al…

cs.LG2026

DP-FedAdamW: An Efficient Optimizer for Differentially Private Federated Large Models

Jin Liu, Yinbin Miao, Ning Xi +1

Balancing convergence efficiency and robustness under Differential Privacy (DP) is a central challenge in Federated Learning (FL). While AdamW accelerates training and fine-tuning…

cs.LG2026

Rethinking LoRA for Privacy-Preserving Federated Learning in Large Models

Jin Liu, Yinbin Miao, Ning Xi +1

Fine-tuning large vision models (LVMs) and large language models (LLMs) under differentially private federated learning (DPFL) is hindered by a fundamental privacy-utility trade-of…

cs.LG2026

Taming Preconditioner Drift: Unlocking the Potential of Second-Order Optimizers for Federated Learning on Non-IID Data

Junkang Liu, Fanhua Shang, Hongying Liu +3

Second-order optimizers can significantly accelerate large-scale training, yet their naive federated variants are often unstable or even diverge on non-IID data. We show that a key…

cs.LG2026

FedAdamW: A Communication-Efficient Optimizer with Convergence and Generalization Guarantees for Federated Large Models

Junkang Liu, Fanhua Shang, Hongying Liu +5

AdamW has become one of the most effective optimizers for training large-scale models. We have also observed its effectiveness in the context of federated learning (FL). However, d…