A Two-Phase Recall-and-Select Framework for Fast Model Selection

arXiv:2404.00069v1 Announce Type: new
Abstract: As the ubiquity of deep learning in various machine learning applications has amplified, a proliferation of neural network models has been trained and shared on public model repositories. In the context of a targeted machine learning assignment, utilizing an apt source model as a starting point typically outperforms the strategy of training from scratch, particularly with limited training data. Despite the investigation and development of numerous model selection strategies in prior work, the process remains …

arxiv cs.lg framework model selection recall type