Transferring Core Knowledge via Learngenes

TL;DR

This paper introduces Genetic Transfer Learning (GTL), a novel framework inspired by natural genetics that transfers essential 'learngenes' to improve neural network performance efficiently and adaptively across tasks.

Contribution

It proposes a new GTL framework that mimics biological evolution to transfer core knowledge via learngenes, enhancing neural networks with fewer parameters and better adaptability.

Findings

Learngenes improve accuracy by 12-16% on CIFAR-FS and miniImageNet.

GTL achieves high scalability and adaptability across network structures and datasets.

Learngenes enable descendant networks to inherit instincts and strong learning abilities.

Abstract

The pre-training paradigm fine-tunes the models trained on large-scale datasets to downstream tasks with enhanced performance. It transfers all knowledge to downstream tasks without discriminating which part is necessary or unnecessary, which may lead to negative transfer. In comparison, knowledge transfer in nature is much more efficient. When passing genetic information to descendants, ancestors encode only the essential knowledge into genes, which act as the medium. Inspired by that, we adopt a recent concept called ``learngene'' and refine its structures by mimicking the structures of natural genes. We propose the Genetic Transfer Learning (GTL) -- a framework to copy the evolutionary process of organisms into neural networks. GTL trains a population of networks, selects superior learngenes by tournaments, performs learngene mutations, and passes the learngenes to next generations. Finally, we successfully extract the learngenes of VGG11 and ResNet12. We show that the learngenes bring the descendant networks instincts and strong learning ability: with 20% parameters, the learngenes bring 12% and 16% improvements of accuracy on CIFAR-FS and miniImageNet. Besides, the learngenes have the scalability and adaptability on the downstream structure of networks and datasets. Overall, we offer a novel insight that transferring core knowledge via learngenes may be sufficient and efficient for neural networks.