Transferable AutoML by Model Sharing Over Grouped Datasets

By Chao Xue, Junchi Yan, Rong Yan, Stephen M. Chu, Yonggang Hu, Yonghua Lin. 2019

24 citations recorded by the source corpus.

Automated Machine Learning (AutoML) is an active area on the design of deep neural networks for specific tasks and datasets. Given the complexity of discovering new network designs, methods for speeding up the search procedure are becoming important. This paper presents a so-called transferable AutoML approach that Automated Machine Learning (AutoML) is an active area on the design of deep neural networks for specific tasks and datasets. Given the complexity of discovering new network designs, methods for speeding up the search procedure are becoming important. This paper presents a so-called transferable AutoML approach that leverages previously trained models to speed up the search process for new tasks and datasets. Our approach involves a novel meta-feature extraction technique based on the performance of benchmark models, and a dynamic dataset clustering algorithm based on Markov process and statistical hypothesis test. As such multiple models can share a common structure while with different learned parameters. The transferable AutoML can either be applied to search from scratch, search from predesigned models, or transfer from basic cells according to the difficulties of the given datasets. The experimental results on image classification show notable speedup in overall search time for multiple datasets with negligible loss in accuracy.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Tejaswini Pedapati
2. Ambrish Rawat
3. Martin Wistuba
4. Marco F. Huber
5. Marc-André Zöller

In Computer Vision and Pattern Recognition

1. Tejaswini Pedapati
2. Ambrish Rawat
3. Martin Wistuba

Citations in the corpus

• A Survey on Neural Architecture Search (2019, methodology): “Xue et al. (2019) Xue et al. (2019) assume a lifelong neural architecture search setting with an incoming stream of datasets.”