# Learning Abstract Task Representations

arXiv: https://arxiv.org/abs/2101.07852 · HTML: https://mlsanity.com/paper/2101.07852/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 26 references that are in the map.
- First posted on arXiv 19 Jan 2021.

## Builds on (most cited first, 10 of 10)

- [Fast R-CNN](https://mlsanity.com/paper/1504.08083/) (2015)
- [Meta-Learning in Neural Networks: A Survey](https://mlsanity.com/paper/2004.05439/) (2020)
- [OpenML: networked science in machine learning](https://mlsanity.com/paper/1407.7722/) (2014)
- [Meta-Learning: A Survey](https://mlsanity.com/paper/1810.03548/) (2018)
- [Task2Vec: Task Embedding for Meta-Learning](https://mlsanity.com/paper/1902.03545/) (2019)
- [Time for a change: a tutorial for comparing multiple classifiers through Bayesian analysis](https://mlsanity.com/paper/1606.04316/) (2016)
- [How Complex is your classification problem? A survey on measuring classification complexity](https://mlsanity.com/paper/1808.03591/) (2018)
- [Dataset2Vec: Learning Dataset Meta-Features](https://mlsanity.com/paper/1905.11063/) (2019)
- [Characterizing classification datasets: a study of meta-features for meta-learning](https://mlsanity.com/paper/1808.10406/) (2018)
- [Examining the Use of Neural Networks for Feature Extraction: A Comparative Analysis using Deep Learning, Support Vector Machines, and K-Nearest Neighbor Classifiers](https://mlsanity.com/paper/1805.02294/) (2018)

## Built on by (most cited first, 3 of 3)

- [Advances in MetaDL: AAAI 2021 challenge and workshop](https://mlsanity.com/paper/2202.01890/) (2022)
- [problexity -- an open-source Python library for binary classification problem complexity assessment](https://mlsanity.com/paper/2207.06709/) (2022)
- [An experimental survey and Perspective View on Meta-Learning for Automated Algorithms Selection and Parametrization](https://mlsanity.com/paper/2504.06207/) (2025)

## Abstract (arXiv)

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.