MGE: A Training-Free and Efficient Model Generation and Enhancement Scheme
Abstract
To provide a foundation for the research of deep learning models, the construction of model pool is an essential step. This paper proposes a Training-Free and Efficient Model Generation and Enhancement Scheme (MGE). This scheme primarily considers two aspects during the model generation process: the distribution of model parameters and model performance. Experiments result shows that generated models are comparable to models obtained through normal training, and even superior in some cases. Moreover, the time consumed in generating models accounts for only 1\% of the time required for normal model training. More importantly, with the enhancement of Evolution-MGE, generated models exhibits competitive generalization ability in few-shot tasks. And the behavioral dissimilarity of generated models has the potential of adversarial defense.
Cite
@article{arxiv.2402.17486,
title = {MGE: A Training-Free and Efficient Model Generation and Enhancement Scheme},
author = {Xuan Wang and Zeshan Pang and Yuliang Lu and Xuehu Yan},
journal= {arXiv preprint arXiv:2402.17486},
year = {2024}
}