Federated Skin Lesion Classification: Efficiency with Skewness-Guided Pruning

This research explores efficient deep learning on edge devices for a critical medical application. The use of skewness-guided pruning for Federated Skin Lesion Classification in a multimodal Swin Transformer architecture is a novel approach to resource constraint AI.

• •Applies pruning techniques (skewness-guided) to optimize a multimodal Swin Transformer.
• •Targets Federated Skin Lesion Classification, a crucial medical application.
• •Focuses on deployment on Edge devices for efficiency.