Ranking architectures using meta-learning
This work addresses the efficiency issue in neural architecture search for researchers and practitioners, but it is incremental as it builds on existing performance prediction methods.
The paper tackles the problem of high computational cost in neural architecture search by introducing a pairwise ranking loss to train a network that ranks candidate architectures for new tasks based on task meta-features, showing it is more effective than previous performance predictors.
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.