Learning Abstract Task Representations
Abstract
A proper form of data characterization can guide the process of learning-algorithm selection and model-performance estimation. The field of meta-learning has provided a rich body of work describing effective forms of data characterization using different families of meta-features (statistical, model-based, information-theoretic, topological, etc.). In this paper, we start with the abundant set of existing meta-features and propose a method to induce new abstract meta-features as latent variables in a deep neural network. We discuss the pitfalls of using traditional meta-features directly and argue for the importance of learning high-level task properties. We demonstrate our methodology using a deep neural network as a feature extractor. We demonstrate that 1) induced meta-models mapping abstract meta-features to generalization performance outperform other methods by ~18% on average, and 2) abstract meta-features attain high feature-relevance scores.
Cite
@article{arxiv.2101.07852,
title = {Learning Abstract Task Representations},
author = {Mikhail M. Meskhi and Adriano Rivolli and Rafael G. Mantovani and Ricardo Vilalta},
journal= {arXiv preprint arXiv:2101.07852},
year = {2021}
}