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 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.
Code (0)
등록된 구현이 없습니다.
Tasks
Meta-LearningNeural Architecture SearchSimilar Papers 제목 키워드 기반
Rankitect: Ranking Architecture Search Battling World-class Engineers at Meta Scale
Neural Architecture Search (NAS) has demonstrated its efficacy in computer vision and potential for ranking systems. However, prior work focused on academic problems, which are evaluated at small scale under well-control…
Neural Architecture SearchFrom Regression to Inference: Meta-Learning Predictors for Neural Architecture Search
Prediction-based approaches are widely used in neural architecture search (NAS), where a predictor estimates the performance of candidate architectures to guide selection. However, existing predictors are typically train…
Neural Architecture SearchSUMNAS: Supernet with Unbiased Meta-Features for Neural Architecture Search
One-shot Neural Architecture Search (NAS) usually constructs an over-parameterized network, which we call a supernet, and typically adopts sharing parameters among the sub-models to improve computational efficiency. One-…
Computational EfficiencyMeta-LearningNeural Architecture SearchEffect of Incomplete Meta-dataset on Average Ranking Method
One of the simplest metalearning methods is the average ranking method. This method uses metadata in the form of test results of a given set of algorithms on given set of datasets and calculates an average rank for each …
Meta-Cal: Well-controlled Post-hoc Calibration by Ranking
In many applications, it is desirable that a classifier not only makes accurate predictions, but also outputs calibrated posterior probabilities. However, many existing classifiers, especially deep neural network classif…
Multi-class Classification