SEArch: A self-evolving framework for network architecture optimization
Yongqing Liang, Dawei Xiang, Xin Shane Li · Neurocomputing · 2025
This paper studies a fundamental network optimization problem that finds a network architecture with optimal performance (low loss) under given resource budgets (small number of parameters and/or fast inference). Unlike existing network optimization approaches such as network pruning, knowledge distillation (KD), and network architecture search (NAS), in this work we introduce a self-evolving pipeline to perform network optimization. In this framework, a simple network iteratively and adaptively modifies its structures by using the guidance from a teacher network, until it reaches the resource budget. An attention module is introduced to transfer the knowledge from the teacher network to the student network. A splitting edge scheme is designed to help the student model find an optimal macro architecture. The proposed framework combines the advantages of pruning, KD, and NAS, and hence, can efficiently generate networks with flexible structure and desirable performance. Extensive experiments on CIFAR-10, CIFAR-100, and ImageNet demonstrated that our framework achieves great performance in this network architecture optimization task.