# Few-shot Open Relation Extraction with Gaussian Prototype and Adaptive Margin

arXiv: https://arxiv.org/abs/2410.20320 · HTML: https://mlsanity.com/paper/2410.20320/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 24 of its 36 references that are in the map.
- First posted on arXiv 27 Oct 2024.

## Builds on (most cited first, 24 of 24)

- [Prototypical Networks for Few-shot Learning](https://mlsanity.com/paper/1703.05175/) (2017)
- [Multi-Similarity Loss with General Pair Weighting for Deep Metric Learning](https://mlsanity.com/paper/1904.06627/) (2019)
- [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)
- [FewRel 2.0: Towards More Challenging Few-Shot Relation Classification](https://mlsanity.com/paper/1910.07124/) (2019)
- [On Generating Plausible Counterfactual and Semi-Factual Explanations for Deep Learning](https://mlsanity.com/paper/2009.06399/) (2020)
- [Few-Shot Open-Set Recognition using Meta-Learning](https://mlsanity.com/paper/2005.13713/) (2020)
- [Packed Levitated Marker for Entity and Relation Extraction](https://mlsanity.com/paper/2109.06067/) (2021)
- [Aligning Instruction Tasks Unlocks Large Language Models as Zero-Shot Relation Extractors](https://mlsanity.com/paper/2305.11159/) (2023)
- [Few-shot Relation Extraction via Bayesian Meta-learning on Relation Graphs](https://mlsanity.com/paper/2007.02387/) (2020)
- [Multi-Level Matching and Aggregation Network for Few-Shot Relation Classification](https://mlsanity.com/paper/1906.06678/) (2019)
- [Should We Rely on Entity Mentions for Relation Extraction? Debiasing Relation Extraction with Counterfactual Analysis](https://mlsanity.com/paper/2205.03784/) (2022)
- [Exploring Task Difficulty for Few-Shot Relation Extraction](https://mlsanity.com/paper/2109.05473/) (2021)
- [Distantly-Supervised Long-Tailed Relation Extraction Using Constraint Graphs](https://mlsanity.com/paper/2105.11225/) (2021)
- [A Simple yet Effective Relation Information Guided Approach for Few-Shot Relation Extraction](https://mlsanity.com/paper/2205.09536/) (2022)
- [Pre-training to Match for Unified Low-shot Relation Extraction](https://mlsanity.com/paper/2203.12274/) (2022)
- [Better Few-Shot Relation Extraction with Label Prompt Dropout](https://mlsanity.com/paper/2210.13733/) (2022)
- [Adaptive Prototypical Networks with Label Words and Joint Representation Learning for Few-Shot Relation Classification](https://mlsanity.com/paper/2101.03526/) (2021)
- [Few-shot Open-set Recognition Using Background as Unknowns](https://mlsanity.com/paper/2207.09059/) (2022)
- [Think Rationally about What You See: Continuous Rationale Extraction for Relation Extraction](https://mlsanity.com/paper/2305.03503/) (2023)
- [Synergistic Anchored Contrastive Pre-training for Few-Shot Relation Extraction](https://mlsanity.com/paper/2312.12021/) (2023)
- [Improving Distantly Supervised Relation Extraction by Natural Language Inference](https://mlsanity.com/paper/2208.00346/) (2022)
- [Jointly Extracting Relations with Class Ties via Effective Deep Ranking](https://mlsanity.com/paper/1612.07602/) (2016)
- [Learning from Semi-Factuals: A Debiased and Semantic-Aware Framework for Generalized Relation Discovery](https://mlsanity.com/paper/2401.06327/) (2024)

## Abstract (arXiv)

Few-shot relation extraction with none-of-the-above (FsRE with NOTA) aims at predicting labels in few-shot scenarios with unknown classes. FsRE with NOTA is more challenging than the conventional few-shot relation extraction task, since the boundaries of unknown classes are complex and difficult to learn. Meta-learning based methods, especially prototype-based methods, are the mainstream solutions to this task. They obtain the classification boundary by learning the sample distribution of each class. However, their performance is limited because few-shot overfitting and NOTA boundary confusion lead to misclassification between known and unknown classes. To this end, we propose a novel framework based on Gaussian prototype and adaptive margin named GPAM for FsRE with NOTA, which includes three modules, semi-factual representation, GMM-prototype metric learning and decision boundary learning. The first two modules obtain better representations to solve the few-shot problem through debiased information enhancement and Gaussian space distance measurement. The third module learns more accurate classification boundaries and prototypes through adaptive margin and negative sampling. In the training procedure of GPAM, we use contrastive learning loss to comprehensively consider the effects of range and margin on the classification of known and unknown classes to ensure the model's stability and robustness. Sufficient experiments and ablations on the FewRel dataset show that GPAM surpasses previous prototype methods and achieves state-of-the-art performance.