# Continual Few-shot Relation Learning via Embedding Space Regularization and Data Augmentation

arXiv: https://arxiv.org/abs/2203.02135 · HTML: https://mlsanity.com/paper/2203.02135/

## Key facts

- Cited by 17 papers in the map (data through 14 Oct 2026).
- Builds on 32 of its 66 references that are in the map.
- First posted on arXiv 4 Mar 2022.

## Builds on (most cited first, 30 of 32)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks](https://mlsanity.com/paper/1703.03400/) (2017)
- [Overcoming catastrophic forgetting in neural networks](https://mlsanity.com/paper/1612.00796/) (2016)
- [Neural Machine Translation of Rare Words with Subword Units](https://mlsanity.com/paper/1508.07909/) (2015)
- [Billion-scale similarity search with GPUs](https://mlsanity.com/paper/1702.08734/) (2017)
- [Learning without Forgetting](https://mlsanity.com/paper/1606.09282/) (2016)
- [iCaRL: Incremental Classifier and Representation Learning](https://mlsanity.com/paper/1611.07725/) (2016)
- [Gradient Episodic Memory for Continual Learning](https://mlsanity.com/paper/1706.08840/) (2017)
- [Progressive Neural Networks](https://mlsanity.com/paper/1606.04671/) (2016)
- [Continual Learning with Deep Generative Replay](https://mlsanity.com/paper/1705.08690/) (2017)
- [Efficient Lifelong Learning with A-GEM](https://mlsanity.com/paper/1812.00420/) (2018)
- [PathNet: Evolution Channels Gradient Descent in Super Neural Networks](https://mlsanity.com/paper/1701.08734/) (2017)
- [Matching the Blanks: Distributional Similarity for Relation Learning](https://mlsanity.com/paper/1906.03158/) (2019)
- [FewRel: A Large-Scale Supervised Few-Shot Relation Classification Dataset with State-of-the-Art Evaluation](https://mlsanity.com/paper/1810.10147/) (2018)
- [Net2Net: Accelerating Learning via Knowledge Transfer](https://mlsanity.com/paper/1511.05641/) (2015)
- [Online Structured Laplace Approximations For Overcoming Catastrophic Forgetting](https://mlsanity.com/paper/1805.07810/) (2018)
- [Few-Shot Incremental Learning with Continually Evolved Classifiers](https://mlsanity.com/paper/2104.03047/) (2021)
- [End-to-End Relation Extraction using LSTMs on Sequences and Tree Structures](https://mlsanity.com/paper/1601.00770/) (2016)
- [LAMOL: LAnguage MOdeling for Lifelong Language Learning](https://mlsanity.com/paper/1909.03329/) (2019)
- [Robust Classification with Convolutional Prototype Learning](https://mlsanity.com/paper/1805.03438/) (2018)
- [LFPT5: A Unified Framework for Lifelong Few-shot Language Learning Based on Prompt Tuning of T5](https://mlsanity.com/paper/2110.07298/) (2021)
- [Self-Promoted Prototype Refinement for Few-Shot Class-Incremental Learning](https://mlsanity.com/paper/2107.08918/) (2021)
- [Sentence Embedding Alignment for Lifelong Relation Extraction](https://mlsanity.com/paper/1903.02588/) (2019)
- [Few-Shot Learning Through an Information Retrieval Lens](https://mlsanity.com/paper/1707.02610/) (2017)
- [Neural Open Information Extraction](https://mlsanity.com/paper/1805.04270/) (2018)
- [One-Shot Generalization in Deep Generative Models](https://mlsanity.com/paper/1603.05106/) (2016)
- [Improved Neural Relation Detection for Knowledge Base Question Answering](https://mlsanity.com/paper/1704.06194/) (2017)
- [One-Shot Unsupervised Cross Domain Translation](https://mlsanity.com/paper/1806.06029/) (2018)
- [Semi-supervised Relation Extraction via Incremental Meta Self-Training](https://mlsanity.com/paper/2010.16410/) (2020)
- [Curriculum-Meta Learning for Order-Robust Continual Relation Extraction](https://mlsanity.com/paper/2101.01926/) (2021)

## Built on by (most cited first, 17 of 17)

- [A Comprehensive Survey of Continual Learning: Theory, Method and Application](https://mlsanity.com/paper/2302.00487/) (2023)
- [Prompt-aligned Gradient for Prompt Tuning](https://mlsanity.com/paper/2205.14865/) (2022)
- [State-of-the-art generalisation research in NLP: A taxonomy and review](https://mlsanity.com/paper/2210.03050/) (2022)
- [In-Context Learning with Iterative Demonstration Selection](https://mlsanity.com/paper/2310.09881/) (2023)
- [Towards Lifelong Learning of Large Language Models: A Survey](https://mlsanity.com/paper/2406.06391/) (2024)
- [A Survey on Few-Shot Class-Incremental Learning](https://mlsanity.com/paper/2304.08130/) (2023)
- [Recent Advances of Foundation Language Models-based Continual Learning: A Survey](https://mlsanity.com/paper/2405.18653/) (2024)
- [Progressive Visual Prompt Learning with Contrastive Feature Re-formation](https://mlsanity.com/paper/2304.08386/) (2023)
- [CITB: A Benchmark for Continual Instruction Tuning](https://mlsanity.com/paper/2310.14510/) (2023)
- [UniS-MMC: Multimodal Classification via Unimodality-supervised Multimodal Contrastive Learning](https://mlsanity.com/paper/2305.09299/) (2023)
- [Lifelong Sequence Generation with Dynamic Module Expansion and Adaptation](https://mlsanity.com/paper/2310.09886/) (2023)
- [Preserving Generalization of Language models in Few-shot Continual Relation Extraction](https://mlsanity.com/paper/2410.00334/) (2024)
- [Serial Contrastive Knowledge Distillation for Continual Few-shot Relation Extraction](https://mlsanity.com/paper/2305.06616/) (2023)
- [Learning to Learn for Few-shot Continual Active Learning](https://mlsanity.com/paper/2311.03732/) (2023)
- [Beyond Output Matching: Bidirectional Alignment for Enhanced In-Context Learning](https://mlsanity.com/paper/2312.17055/) (2023)
- [Expanding continual few-shot learning benchmarks to include recognition of specific instances](https://mlsanity.com/paper/2209.07863/) (2022)
- [Few-Shot Relation Extraction with Hybrid Visual Evidence](https://mlsanity.com/paper/2403.00724/) (2024)

## Abstract (arXiv)

Existing continual relation learning (CRL) methods rely on plenty of labeled training data for learning a new task, which can be hard to acquire in real scenario as getting large and representative labeled data is often expensive and time-consuming. It is therefore necessary for the model to learn novel relational patterns with very few labeled data while avoiding catastrophic forgetting of previous task knowledge. In this paper, we formulate this challenging yet practical problem as continual few-shot relation learning (CFRL). Based on the finding that learning for new emerging few-shot tasks often results in feature distributions that are incompatible with previous tasks' learned distributions, we propose a novel method based on embedding space regularization and data augmentation. Our method generalizes to new few-shot tasks and avoids catastrophic forgetting of previous tasks by enforcing extra constraints on the relational embeddings and by adding extra {relevant} data in a self-supervised manner. With extensive experiments we demonstrate that our method can significantly outperform previous state-of-the-art methods in CFRL task settings.