4 papers
Reassessing Global Gradient-Norm Imbalance in BLIP Fine-Tuning Across Physical Domains
Kiran Naseer, Samreen Azhar, Dwarikanath Mahapatra
Imbalanced gradient magnitudes between the visual and language pathways of a vision-language model are often treated as a defect to be corrected. We test that premise for one famil…
Perplexity Predicts Protection: Choosing Pretrained Backbones for Worst-Client Fairness in Federated Parameter-Efficient Fine-Tuning
Kiran Naseer, Samreen Azhar, Umar Shoaib +2
Federated learning lets multiple parties train a shared model without pooling their data, but a client with far less data than the others can end up poorly served even when the gro…
MedFL-Stress: A Systematic Robustness Evaluation of Federated Brain Tumor Segmentation under Cross-Hospital MRI Appearance Shift
Kiran Naseer, Naveed Anwer Butt
Federated learning enables hospitals to collaboratively train segmentation models without sharing patient data. However, current evaluation protocols report only average performanc…
When More Parameters Hurt: Foundation Model Priors Amplify Worst-Client Disparity Under Extreme Federated Heterogeneity
Kiran Naseer, Umar Shoaib
Federated learning (FL) is increasingly used to fine-tune foundation models (FMs) on distributed private data. The community largely assumes that large-scale pretraining serves as…