JIPS (한국정보처리학회)
Current Result Document :
| 한글제목(Korean Title) |
Path-Based Computation Encoder for Neural Architecture Search |
| 영문제목(English Title) |
Path-Based Computation Encoder for Neural Architecture Search |
| 저자(Author) |
Ying Yang
Xu Zhang
Hu Pan
|
| 원문수록처(Citation) |
VOL 18 NO. 02 PP. 0188 ~ 0196 (2022. 04) |
한글내용
(Korean Abstract) |
|
영문내용
(English Abstract) |
Recently, neural architecture search (NAS) has received increasing attention as it can replace human experts in designing the architecture of neural networks for different tasks and has achieved remarkable results in many challenging tasks. In this study, a path-based computation neural architecture encoder (PCE) was proposed. Our PCE first encodes the computation of information on each path in a neural network, and then aggregates the encodings on all paths together through an attention mechanism, simulating the process of information computation along paths in a neural network and encoding the computation on the neural network instead of the structure of the graph, which is more consistent with the computational properties of neural networks. We performed an extensive comparison with eight encoding methods on two commonly used NAS search spaces (NAS-Bench-101 and NAS-Bench-201), which included a comparison of the predictive capabilities of performance predictors and search capabilities based on two search strategies (reinforcement learning-based and Bayesian optimization-based) when equipped with different encoders. Experimental evaluation shows that PCE is an efficient encoding method that effectively ranks and predicts neural architecture performance, thereby improving the search efficiency of neural architectures.
|
| 키워드(Keyword) |
Neural Architecture Search
Path-based Computation
Performance Predictor
|
| 파일첨부 |
PDF 다운로드
|
