TY  - JOUR
T1  - Personalized Federated Post-Training for Real-time Adaptation to Label Distribution Shifts
AU  - Im, Kyungjin 
AU  - Park, Heewon 
AU  - Kim, Miru 
AU  - Joe, Mugon 
AU  - Kwon, Minhae 
JO  - The Journal of Korean Institute of Communications and Information Sciences
PY  - 2025
DA  - 2025/1/1
DO  - 10.7840/kics.2025.50.12.1811
KW  - Federated Learning
KW  - Post-training
KW  - Personalization
KW  - Label Shift
AB  - Artificial intelligence systems deployed to individual devices are exposed to shifting label distributions over time, degrading model performance. While post-training has been studied to address this, limited local data and overfitting can cause loss of critical knowledge in the pre-trained model. We propose Fed-AFIR(Federated Adaptation with FIM Regularization), leveraging the Fisher Information Matrix (FIM) to preserve critical parameters while enabling collaboration across devices, consistently outperforming existing approaches under dynamic label distribution and heterogeneous device data conditions.