Model Selection with Model Zoo via Graph Learning

arXiv:2404.03988v1 Announce Type: new
Abstract: Pre-trained deep learning (DL) models are increasingly accessible in public repositories, i.e., model zoos. Given a new prediction task, finding the best model to fine-tune can be computationally intensive and costly, especially when the number of pre-trained models is large. Selecting the right pre-trained models is crucial, yet complicated by the diversity of models from various model families (like ResNet, Vit, Swin) and the hidden relationships between models and datasets. Existing methods, which utilize basic …

abstract arxiv cs.lg cs.si deep learning graph graph learning model selection prediction pre-trained models public repositories type via