3 papers
cs.LG2025
FedNoisy: Federated Noisy Label Learning Benchmark
Siqi Liang, Jintao Huang, Junyuan Hong +3
Federated learning has gained popularity for distributed learning without aggregating sensitive data from clients. But meanwhile, the distributed and isolated nature of data isolat…
cs.CR2024
FewFedPIT: Towards Privacy-preserving and Few-shot Federated Instruction Tuning
Zhuo Zhang, Jingyuan Zhang, Jintao Huang +5
Instruction tuning has been identified as a crucial technique for optimizing the performance of large language models (LLMs) in generating human-aligned responses. Nonetheless, gat…
cs.AI2024
UniDM: A Unified Framework for Data Manipulation with Large Language Models
Yichen Qian, Yongyi He, Rong Zhu +8
Designing effective data manipulation methods is a long standing problem in data lakes. Traditional methods, which rely on rules or machine learning models, require extensive human…