# Neural Snowball for Few-Shot Relation Learning

arXiv: https://arxiv.org/abs/1908.11007 · HTML: https://mlsanity.com/paper/1908.11007/

## Key facts

- Cited by 22 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 29 Aug 2019.

## Built on by (most cited first, 22 of 22)

- [KnowPrompt: Knowledge-aware Prompt-tuning with Synergistic Optimization for Relation Extraction](https://mlsanity.com/paper/2104.07650/) (2021)
- [A Comprehensive Survey of Few-shot Learning: Evolution, Applications, Challenges, and Opportunities](https://mlsanity.com/paper/2205.06743/) (2022)
- [LFPT5: A Unified Framework for Lifelong Few-shot Language Learning Based on Prompt Tuning of T5](https://mlsanity.com/paper/2110.07298/) (2021)
- [In-Context Learning with Iterative Demonstration Selection](https://mlsanity.com/paper/2310.09881/) (2023)
- [Continual Training of Language Models for Few-Shot Learning](https://mlsanity.com/paper/2210.05549/) (2022)
- [Continual Few-shot Relation Learning via Embedding Space Regularization and Data Augmentation](https://mlsanity.com/paper/2203.02135/) (2022)
- [Few-shot Named Entity Recognition with Entity-level Prototypical Network Enhanced by Dispersedly Distributed Prototypes](https://mlsanity.com/paper/2208.08023/) (2022)
- [A Survey of Imbalanced Learning on Graphs: Problems, Techniques, and Future Directions](https://mlsanity.com/paper/2308.13821/) (2023)
- [Linguistically-Enriched and Context-Aware Zero-shot Slot Filling](https://mlsanity.com/paper/2101.06514/) (2021)
- [Learning to Initialize: Can Meta Learning Improve Cross-task Generalization in Prompt Tuning?](https://mlsanity.com/paper/2302.08143/) (2023)
- [What Can Knowledge Bring to Machine Learning? -- A Survey of Low-shot Learning for Structured Data](https://mlsanity.com/paper/2106.06410/) (2021)
- [Grasping the Essentials: Tailoring Large Language Models for Zero-Shot Relation Extraction](https://mlsanity.com/paper/2402.11142/) (2024)
- [Learning to Bridge Metric Spaces: Few-shot Joint Learning of Intent Detection and Slot Filling](https://mlsanity.com/paper/2106.07343/) (2021)
- [MORE: A Metric Learning Based Framework for Open-domain Relation Extraction](https://mlsanity.com/paper/2206.00289/) (2022)
- [Beyond Output Matching: Bidirectional Alignment for Enhanced In-Context Learning](https://mlsanity.com/paper/2312.17055/) (2023)
- [ConstGCN: Constrained Transmission-based Graph Convolutional Networks for Document-level Relation Extraction](https://mlsanity.com/paper/2210.03949/) (2022)
- [QASnowball: An Iterative Bootstrapping Framework for High-Quality Question-Answering Data Generation](https://mlsanity.com/paper/2309.10326/) (2023)
- [A systematic review of relation extraction task since the emergence of Transformers](https://mlsanity.com/paper/2511.03610/) (2025)
- [Few-Shot Relation Extraction with Hybrid Visual Evidence](https://mlsanity.com/paper/2403.00724/) (2024)
- [Towards Human-Like Machine Comprehension: Few-Shot Relational Learning in Visually-Rich Documents](https://mlsanity.com/paper/2403.15765/) (2024)
- [A Continual Relation Extraction Approach for Knowledge Graph Completeness](https://mlsanity.com/paper/2404.17593/) (2024)
- [M-BRe: Discovering Training Samples for Relation Extraction from Unlabeled Texts with Large Language Models](https://mlsanity.com/paper/2509.07730/) (2025)

## Abstract (arXiv)

Knowledge graphs typically undergo open-ended growth of new relations. This cannot be well handled by relation extraction that focuses on pre-defined relations with sufficient training data. To address new relations with few-shot instances, we propose a novel bootstrapping approach, Neural Snowball, to learn new relations by transferring semantic knowledge about existing relations. More specifically, we use Relational Siamese Networks (RSN) to learn the metric of relational similarities between instances based on existing relations and their labeled data. Afterwards, given a new relation and its few-shot instances, we use RSN to accumulate reliable instances from unlabeled corpora; these instances are used to train a relation classifier, which can further identify new facts of the new relation. The process is conducted iteratively like a snowball. Experiments show that our model can gather high-quality instances for better few-shot relation learning and achieves significant improvement compared to baselines. Codes and datasets are released on https://github.com/thunlp/Neural-Snowball.