Neural Architecture Search based on Cartesian Genetic Programming Coding Method
This work addresses automated neural architecture design for natural language processing tasks, but it is incremental as it applies an existing evolutionary method to a specific domain.
The authors tackled neural architecture search for sentence classification by proposing CGPNAS, an evolutionary approach based on Cartesian genetic programming, and found that the searched architectures achieved performance comparable to human-designed ones with domain transfer accuracy deterioration of 2-5%.
Neural architecture search (NAS) is a hot topic in the field of automated machine learning and outperforms humans in designing neural architectures on quite a few machine learning tasks. Motivated by the natural representation form of neural networks by the Cartesian genetic programming (CGP), we propose an evolutionary approach of NAS based on CGP, called CGPNAS, to solve sentence classification task. To evolve the architectures under the framework of CGP, the operations such as convolution are identified as the types of function nodes of CGP, and the evolutionary operations are designed based on Evolutionary Strategy. The experimental results show that the searched architectures are comparable with the performance of human-designed architectures. We verify the ability of domain transfer of our evolved architectures. The transfer experimental results show that the accuracy deterioration is lower than 2-5%. Finally, the ablation study identifies the Attention function as the single key function node and the linear transformations along could keep the accuracy similar with the full evolved architectures, which is worthy of investigation in the future.