Graph Masked Autoencoder Enhanced Predictor for Neural Architecture Search
Gespeichert in:
| Titel: | Graph Masked Autoencoder Enhanced Predictor for Neural Architecture Search |
|---|---|
| Autoren: | Kun Jing, Jungang Xu, Pengfei Li |
| Quelle: | Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence. :3114-3120 |
| Verlagsinformationen: | International Joint Conferences on Artificial Intelligence Organization, 2022. |
| Publikationsjahr: | 2022 |
| Schlagwörter: | 0202 electrical engineering, electronic engineering, information engineering, 02 engineering and technology |
| Beschreibung: | Performance estimation of neural architecture is a crucial component of neural architecture search (NAS). Meanwhile, neural predictor is a current mainstream performance estimation method. However, it is a challenging task to train the predictor with few architecture evaluations for efficient NAS. In this paper, we propose a graph masked autoencoder (GMAE) enhanced predictor, which can reduce the dependence on supervision data by self-supervised pre-training with untrained architectures. We compare our GMAE-enhanced predictor with existing predictors in different search spaces, and experimental results show that our predictor has high query utilization. Moreover, GMAE-enhanced predictor with different search strategies can discover competitive architectures in different search spaces. Code and supplementary materials are available at https://github.com/kunjing96/GMAENAS.git. |
| Publikationsart: | Article |
| DOI: | 10.24963/ijcai.2022/432 |
| Dokumentencode: | edsair.doi...........5cd3f94a20b667ca8fa31c13bf6c621c |
| Datenbank: | OpenAIRE |
Nájsť tento článok vo Web of Science Schreiben Sie den ersten Kommentar!