# Worst-Case-Aware Curriculum Learning for Zero and Few Shot Transfer

arXiv: https://arxiv.org/abs/2009.11138 · HTML: https://mlsanity.com/paper/2009.11138/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 23 Sep 2020.

## Built on by (most cited first, 6 of 6)

- [Curriculum Learning: A Survey](https://mlsanity.com/paper/2101.10382/) (2021)
- [Challenges and Strategies in Cross-Cultural NLP](https://mlsanity.com/paper/2203.10020/) (2022)
- [Turning Tables: Generating Examples from Semi-structured Tables for Endowing Language Models with Reasoning Skills](https://mlsanity.com/paper/2107.07261/) (2021)
- [Minimax and Neyman-Pearson Meta-Learning for Outlier Languages](https://mlsanity.com/paper/2106.01051/) (2021)
- [Zero-Shot Dependency Parsing with Worst-Case Aware Automated Curriculum Learning](https://mlsanity.com/paper/2203.08555/) (2022)
- [Curriculum Meta-Learning for Few-shot Classification](https://mlsanity.com/paper/2112.02913/) (2021)

## Abstract (arXiv)

Multi-task transfer learning based on pre-trained language encoders achieves state-of-the-art performance across a range of tasks. Standard approaches implicitly assume the tasks, for which we have training data, are equally representative of the tasks we are interested in, an assumption which is often hard to justify. This paper presents a more agnostic approach to multi-task transfer learning, which uses automated curriculum learning to minimize a new family of worst-case-aware losses across tasks. Not only do these losses lead to better performance on outlier tasks; they also lead to better performance in zero-shot and few-shot transfer settings.