# Inconsistent Few-Shot Relation Classification via Cross-Attentional Prototype Networks with Contrastive Learning

arXiv: https://arxiv.org/abs/2110.08254 · HTML: https://mlsanity.com/paper/2110.08254/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 29 references that are in the map.
- First posted on arXiv 13 Oct 2021.

## Builds on (most cited first, 19 of 19)

- [Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks](https://mlsanity.com/paper/1703.03400/) (2017)
- [Prototypical Networks for Few-shot Learning](https://mlsanity.com/paper/1703.05175/) (2017)
- [Matching Networks for One Shot Learning](https://mlsanity.com/paper/1606.04080/) (2016)
- [On First-Order Meta-Learning Algorithms](https://mlsanity.com/paper/1803.02999/) (2018)
- [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)
- [Simple BERT Models for Relation Extraction and Semantic Role Labeling](https://mlsanity.com/paper/1904.05255/) (2019)
- [FewRel 2.0: Towards More Challenging Few-Shot Relation Classification](https://mlsanity.com/paper/1910.07124/) (2019)
- [Few-shot Natural Language Generation for Task-Oriented Dialog](https://mlsanity.com/paper/2002.12328/) (2020)
- [Few-shot Slot Tagging with Collapsed Dependency Transfer and Label-enhanced Task-adaptive Projection Network](https://mlsanity.com/paper/2006.05702/) (2020)
- [A Theoretical Analysis of the Number of Shots in Few-Shot Learning](https://mlsanity.com/paper/1909.11722/) (2019)
- [Few-shot Relation Extraction via Bayesian Meta-learning on Relation Graphs](https://mlsanity.com/paper/2007.02387/) (2020)
- [Coach: A Coarse-to-Fine Approach for Cross-domain Slot Filling](https://mlsanity.com/paper/2004.11727/) (2020)
- [Prototypical Representation Learning for Relation Extraction](https://mlsanity.com/paper/2103.11647/) (2021)
- [Multi-Level Matching and Aggregation Network for Few-Shot Relation Classification](https://mlsanity.com/paper/1906.06678/) (2019)
- [Meta-Learning for Low-resource Natural Language Generation in Task-oriented Dialogue Systems](https://mlsanity.com/paper/1905.05644/) (2019)
- [Zero-Shot Adaptive Transfer for Conversational Language Understanding](https://mlsanity.com/paper/1808.10059/) (2018)
- [Improved Relation Extraction with Feature-Rich Compositional Embedding Models](https://mlsanity.com/paper/1505.02419/) (2015)
- [MCML: A Novel Memory-based Contrastive Meta-Learning Method for Few Shot Slot Tagging](https://mlsanity.com/paper/2108.11635/) (2021)

## Built on by (most cited first, 1 of 1)

- [Has It All Been Solved? Open NLP Research Questions Not Solved by Large Language Models](https://mlsanity.com/paper/2305.12544/) (2023)

## Abstract (arXiv)

Standard few-shot relation classification (RC) is designed to learn a robust classifier with only few labeled data for each class. However, previous works rarely investigate the effects of a different number of classes (i.e., N-way) and number of labeled data per class (i.e., K-shot) during training vs. testing. In this work, we define a new task, textitinconsistent few-shot RC, where the model needs to handle the inconsistency of N and K between training and testing. To address this new task, we propose Prototype Network-based cross-attention contrastive learning (ProtoCACL) to capture the rich mutual interactions between the support set and query set. Experimental results demonstrate that our ProtoCACL can outperform the state-of-the-art baseline model under both inconsistent K and inconsistent N settings, owing to its more robust and discriminate representations. Moreover, we identify that in the inconsistent few-shot learning setting, models can achieve better performance with textitless data than the standard few-shot setting with carefully-selected N and K. In the end of the paper, we provide further analyses and suggestions to systematically guide the selection of N and K under different scenarios.