← Search

Zhihao Qu

2 accepted papers

2023

Anchor Sampling for Federated Learning with Partial Client Participation

ICML 2023poster

Compared with full client participation, partial client participation is a more practical scenario in federated learning, but it may amplify some challenges in federated learning, such as data heterogeneity. The lack of inactive clients' updates in partial client participation makes it more likely f…

2022

Hierarchical Channel-spatial Encoding for Communication-efficient Collaborative Learning

NeurIPS 2022accept

It witnesses that the collaborative learning (CL) systems often face the performance bottleneck of limited bandwidth, where multiple low-end devices continuously generate data and transmit intermediate features to the cloud for incremental training. To this end, improving the communication efficienc…

Cited by 5SourcePDFScholar