activity
20222026
most citedFedDisco: Federated Learning with Discrepancy-Aware Collaboration

25 citations · 63 across the 37 of their papers we have counts for

collaborators
Showing cs.LGShow all

9 papers · 1 filter

cs.LG2024

Data Quality Control in Federated Instruction-tuning of Large Language Models

Yaxin Du, Rui Ye, Fengting Yuchi +4

Federated Learning (FL) enables privacy-preserving collaborative instruction tuning of large language models (LLMs) by leveraging massively distributed data. However, the decentral…

cs.LG2024

Optimizing Cross-Client Domain Coverage for Federated Instruction Tuning of Large Language Models

Zezhou Wang, Yaxin Du, Xingjun Ma +3

Federated domain-specific instruction tuning (FedDIT) for large language models (LLMs) aims to enhance performance in specialized domains using distributed private and limited data…

cs.LG2024★ 1 cited

Enhancing Data Quality in Federated Fine-Tuning of Foundation Models

Wanru Zhao, Yaxin Du, Nicholas Donald Lane +2

In the current landscape of foundation model training, there is a significant reliance on public domain data, which is nearing exhaustion according to recent research. To further s…

cs.LG2024★ 7 cited

OpenFedLLM: Training Large Language Models on Decentralized Private Data via Federated Learning

Rui Ye, Wenhao Wang, Jingyi Chai +6

Trained on massive publicly available data, large language models (LLMs) have demonstrated tremendous success across various fields. While more data contributes to better performan…

cs.LG2024

Learn What You Need in Personalized Federated Learning

Kexin Lv, Rui Ye, Xiaolin Huang +2

Personalized federated learning aims to address data heterogeneity across local clients in federated learning. However, current methods blindly incorporate either full model parame…

cs.LG2023★ 2 cited

Fake It Till Make It: Federated Learning with Consensus-Oriented Generation

Rui Ye, Yaxin Du, Zhenyang Ni +2

In federated learning (FL), data heterogeneity is one key bottleneck that causes model divergence and limits performance. Addressing this, existing methods often regard data hetero…