← Search

Chenyu Song

2 accepted papers

2025

Rising from Ashes: Generalized Federated Learning via Dynamic Parameter Reset

NeurIPS 2025poster

Although Federated Learning (FL) is promising in privacy-preserving collaborative model training, it faces low inference performance due to heterogeneous data among clients. Due to heterogeneous data in each client, FL training easily learns the specific overfitting features. Existing FL methods ad…

Cited by 0SourceScholar
2024

Pure Exploration in Asynchronous Federated Bandits

UAI 2024poster

We study the federated pure exploration problem of multi-armed bandits and linear bandits, where $M$ agents cooperatively identify the best arm via communicating with the central server. To enhance the robustness against latency and unavailability of agents that are common in practice, we propose th…

Cited by 1SourcePDFScholar