# Knowledge Guided Metric Learning for Few-Shot Text Classification

arXiv: https://arxiv.org/abs/2004.01907 · HTML: https://mlsanity.com/paper/2004.01907/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 4 Apr 2020.

## Built on by (most cited first, 8 of 8)

- [Adversarial Feature Augmentation for Cross-domain Few-shot Classification](https://mlsanity.com/paper/2208.11021/) (2022)
- [Zero-shot and Few-shot Learning with Knowledge Graphs: A Comprehensive Survey](https://mlsanity.com/paper/2112.10006/) (2021)
- [Imagination-Augmented Natural Language Understanding](https://mlsanity.com/paper/2204.08535/) (2022)
- [What Can Knowledge Bring to Machine Learning? -- A Survey of Low-shot Learning for Structured Data](https://mlsanity.com/paper/2106.06410/) (2021)
- [PromptDA: Label-guided Data Augmentation for Prompt-based Few-shot Learners](https://mlsanity.com/paper/2205.09229/) (2022)
- [Improving Few-shot Generalization of Safety Classifiers via Data Augmented Parameter-Efficient Fine-Tuning](https://mlsanity.com/paper/2310.16959/) (2023)
- [Retrieval-Augmented Meta Learning for Low-Resource Text Classification](https://mlsanity.com/paper/2309.04979/) (2023)
- [Fast Learning of Dynamic Hand Gesture Recognition with Few-Shot Learning Models](https://mlsanity.com/paper/2212.08363/) (2022)

## Abstract (arXiv)

The training of deep-learning-based text classification models relies heavily on a huge amount of annotation data, which is difficult to obtain. When the labeled data is scarce, models tend to struggle to achieve satisfactory performance. However, human beings can distinguish new categories very efficiently with few examples. This is mainly due to the fact that human beings can leverage knowledge obtained from relevant tasks. Inspired by human intelligence, we propose to introduce external knowledge into few-shot learning to imitate human knowledge. A novel parameter generator network is investigated to this end, which is able to use the external knowledge to generate relation network parameters. Metrics can be transferred among tasks when equipped with these generated parameters, so that similar tasks use similar metrics while different tasks use different metrics. Through experiments, we demonstrate that our method outperforms the state-of-the-art few-shot text classification models.