ICML 2022spotlight16 citations

Zero-shot AutoML with Pretrained Models

Ekrem Öztürk, Fabio Ferreira, Hadi Jomaa, Lars Schmidt-Thieme, Josif Grabocka, Frank Hutter

Abstract

Given a new dataset D and a low compute budget, how should we choose a pre-trained model to fine-tune to D, and set the fine-tuning hyperparameters without risking overfitting, particularly if D is small? Here, we extend automated machine learning (AutoML) to best make these choices. Our domain-independent meta-learning approach learns a zero-shot surrogate model which, at test time, allows to select the right deep learning (DL) pipeline (including the pre-trained model and fine-tuning hyperparameters) for a new dataset D given only trivial meta-features describing D such as image resolution or the number of classes. To train this zero-shot model, we collect performance data for many DL pipelines on a large collection of datasets and meta-train on this data to minimize a pairwise ranking objective. We evaluate our approach under the strict time limit of the vision track of the ChaLearn AutoDL challenge benchmark, clearly outperforming all challenge contenders.

BibTeX
@InProceedings{pmlr-v162-ozturk22a,
  title = 	 {Zero-shot {A}uto{ML} with Pretrained Models},
  author =       {{\"O}zt{\"u}rk, Ekrem and Ferreira, Fabio and Jomaa, Hadi and Schmidt-Thieme, Lars and Grabocka, Josif and Hutter, Frank},
  booktitle = 	 {Proceedings of the 39th International Conference on Machine Learning},
  pages = 	 {17138--17155},
  year = 	 {2022},
  editor = 	 {Chaudhuri, Kamalika and Jegelka, Stefanie and Song, Le and Szepesvari, Csaba and Niu, Gang and Sabato, Sivan},
  volume = 	 {162},
  series = 	 {Proceedings of Machine Learning Research},
  month = 	 {17--23 Jul},
  publisher =    {PMLR},
  pdf = 	 {https://proceedings.mlr.press/v162/ozturk22a/ozturk22a.pdf},
  url = 	 {https://proceedings.mlr.press/v162/ozturk22a.html},
  abstract = 	 {Given a new dataset D and a low compute budget, how should we choose a pre-trained model to fine-tune to D, and set the fine-tuning hyperparameters without risking overfitting, particularly if D is small? Here, we extend automated machine learning (AutoML) to best make these choices. Our domain-independent meta-learning approach learns a zero-shot surrogate model which, at test time, allows to select the right deep learning (DL) pipeline (including the pre-trained model and fine-tuning hyperparameters) for a new dataset D given only trivial meta-features describing D such as image resolution or the number of classes. To train this zero-shot model, we collect performance data for many DL pipelines on a large collection of datasets and meta-train on this data to minimize a pairwise ranking objective. We evaluate our approach under the strict time limit of the vision track of the ChaLearn AutoDL challenge benchmark, clearly outperforming all challenge contenders.}
}