@inproceedings{772b0c1a5c9f472283966096bc2e7de4,
title = "TRIO: Task-agnostic dataset representation optimized for automatic algorithm selection",
abstract = "With the growing number of machine learning (ML) algorithms, the selection of the top-performing algorithms for a given dataset, task, and evaluation measure is known to be a challenging task. The human expertise required for this task has fueled the demand for automatic solutions. Meta-learning is a popular approach for automatic algorithm selection based on dataset characterization. Existing meta-learning methods often represent the datasets using predefined features and thus cannot be generalized for various ML tasks, or alternatively, learn their representations in a supervised fashion, and thus cannot address unsupervised tasks. In this study, we first propose a novel learning-based task-agnostic method for dataset representation. Second, we present TRIO, a meta-learning approach based on the proposed dataset representation, which is capable of accurately recommending top-performing algorithms for unseen datasets. TRIO first learns graphical representations from the datasets and then utilizes a graph convolutional neural network technique to extract their latent representations. An extensive evaluation on 337 datasets and 195 ML algorithms demonstrates the effectiveness of our approach over state-of-the-art methods for algorithm selection for both supervised (classification and regression) and unsupervised (clustering) tasks.",
keywords = "algorithm selection, AutoML, meta-learning, task-agnostic dataset representation",
author = "Noy Cohen-Shapira and Lior Rokach",
note = "Publisher Copyright: {\textcopyright} 2021 IEEE.; 21st IEEE International Conference on Data Mining, ICDM 2021 ; Conference date: 07-12-2021 Through 10-12-2021",
year = "2021",
month = jan,
day = "1",
doi = "10.1109/ICDM51629.2021.00018",
language = "English",
series = "Proceedings - IEEE International Conference on Data Mining, ICDM",
publisher = "Institute of Electrical and Electronics Engineers",
pages = "81--90",
editor = "James Bailey and Pauli Miettinen and Koh, {Yun Sing} and Dacheng Tao and Xindong Wu",
booktitle = "Proceedings - 21st IEEE International Conference on Data Mining, ICDM 2021",
address = "United States",
}