Song Han
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Song Han has a total of 4 co-authors. Here are the top co-authors by number of shared publications:
- Ming Wang
Trine University, USA
1 shared publication - Sibo Wang
Rice University, USA
1 shared publication - Yilin Li
Carnegie Mellon University, USA
1 shared publication - Ziyu Cheng
University of Southern California, USA
1 shared publication
Latest Publications
- Open Access
- 18 September 2025
- Published by MDPI AG in Preprints.org
Federated Fine‐Tuning of Large Language Models with Privacy Preservation and Cross‐Domain Semantic Alignment
This paper presents a federated fine-tuning framework for large language models that addresses the challenges of multi-source heterogeneity and privacy sensitivity. The method incorporates a differential privacy perturbation strategy at the local client level to protect sensitive gradient information and prevent data leakage during cross-device collaboration. A domain adaptation module based on feature distribution alignment is introduced to reduce semantic shifts between source and target domains using maximum mean discrepancy optimization and attention-guided mechanisms. The overall architecture integrates local modeling with global parameter aggregation, forming a closed loop of federated alignment and global integration for efficient, secure, and cross-domain semantic modeling. The experimental design includes multidimensional sensitivity evaluations across privacy perturbation levels, label missingness, and domain distribution shifts. Results demonstrate that the proposed method achieves superior performance in key metrics such as Perplexity, MMD, and Domain Accuracy, confirming its effectiveness in jointly optimizing privacy protection and cross-domain generalization.
- 18 September 2025
- Published by MDPI AG in Preprints.org
Open AccessFederated Fine‐Tuning of Large Language Models with Privacy Preservation and Cross‐Domain Semantic Alignment
This paper presents a federated fine-tuning framework for large language models that addresses the challenges of multi-source heterogeneity and privacy sensitivity. The method incorporates a differential privacy perturbation strategy at the local client level to protect sensitive gradient information and prevent data leakage during cross-device collaboration. A domain adaptation module based on feature distribution alignment is introduced to reduce semantic shifts between source and target domains using maximum mean discrepancy optimization and attention-guided mechanisms. The overall architecture integrates local modeling with global parameter aggregation, forming a closed loop of federated alignment and global integration for efficient, secure, and cross-domain semantic modeling. The experimental design includes multidimensional sensitivity evaluations across privacy perturbation levels, label missingness, and domain distribution shifts. Results demonstrate that the proposed method achieves superior performance in key metrics such as Perplexity, MMD, and Domain Accuracy, confirming its effectiveness in jointly optimizing privacy protection and cross-domain generalization.