Ranking architectures using meta-learning

Neural architecture search has recently attracted lots of research efforts as it promises to automate the manual design of neural networks. However, it requires a large amount of computing resources and in order to alleviate this, a performance prediction network has been recently proposed that enab...

Full description

Saved in:
Bibliographic Details
Published in:arXiv.org 2019-11
Main Authors: Dubatovka, Alina, Kokiopoulou, Efi, Sbaiz, Luciano, Gesmundo, Andrea, Bartok, Gabor, Berent, Jesse
Format: Article
Language:English
Subjects:
Architecture
Neural networks
Performance prediction
Ranking
Searching
Training
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Neural architecture search has recently attracted lots of research efforts as it promises to automate the manual design of neural networks. However, it requires a large amount of computing resources and in order to alleviate this, a performance prediction network has been recently proposed that enables efficient architecture search by forecasting the performance of candidate architectures, instead of relying on actual model training. The performance predictor is task-aware taking as input not only the candidate architecture but also task meta-features and it has been designed to collectively learn from several tasks. In this work, we introduce a pairwise ranking loss for training a network able to rank candidate architectures for a new unseen task conditioning on its task meta-features. We present experimental results, showing that the ranking network is more effective in architecture search than the previously proposed performance predictor.
ISSN:2331-8422