Author

Wei Guan

2 papers indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

2026

FedAD: An Adaptive Block Dropping Approach for Federated Learning on Resource-Constrained Devices

—In a federated learning environment with heterogeneous, limited and time-varying computational resource capabilities, it is challenging to update deep neural network in real-time. To address this challenge, we propose FedAD, an adaptive block-dropping approach for federated learning on resource-constrained devices. Fe...

Qi-Qi Cai, Jian Cao, Jian-Qing Zhang et al. · IEEE Transactions on Paralle... · 0 citations

#artificial intelligence Dec 2025

GLOW: Graph-Language Co-Encoding for Agentic Workflow Performance Prediction

GLOW is proposed, a unified framework for AW performance prediction that combines the graph-structure modeling ability of GNNs with the topology-aware semantic encoding capability of LLMs and consistently outperforms state-of-the-art baselines in both prediction accuracy and ranking utility.

Wei Guan, Jian Cao, Jin-Yu Cai et al. · IEEE Transactions on Service... · 2 citations