Skip to content
conftrace_

Junkang Liu

3 papers · 2025–2026 · 3 venues · across top CS/AI venues

Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.

Achievements

Jump to papers ↓
🌍 Conference Polyglot · Bronze 🌉 Interdisciplinary Bridge · Bronze

Venues

AAAI (1) CVPR (1) ICML (1)

Top co-authors

Jin Liu (3) Fanhua Shang (2) Hongying Liu (2) Yuanyuan Liu (2) Ning Xi (1) Kewen Zhu (1) Yuxuan Tian (1) Wei Feng (1) Yinbin Miao (1) Zhouchen Lin (1)

Research topics

Machine Learning (3) Optimization & Theory (3) Artificial Intelligence (1) Deep Learning (1) Mathematics & Optimization (1) Application Areas (1) Learning Paradigms (1) Learning Types · Deep Learning (1) Learning Types · Machine Learning (1) Optimization (1)

Keywords

federated learning (3) differential privacy (1) convergence analysis (1) neural network optimization (1) generalization (1) convergence rate (1) data heterogeneity (1) weight decay (1) heterogeneous data (1) stochastic weight averaging (1) client drift (1) momentum-based (1)

Papers

DP-FedAdamW: An Efficient Optimizer for Differentially Private Federated Large Models CVPR 2026 FedAdamW: A Communication-Efficient Optimizer with Convergence and Generalization Guarantees for Federated Large Models AAAI 2026 Improving Generalization in Federated Learning with Highly Heterogeneous Data via Momentum-Based Stochastic Controlled Weight Averaging ICML 2025