# Ensemble Making Few-Shot Learning Stronger

arXiv: https://arxiv.org/abs/2105.11904 · HTML: https://mlsanity.com/paper/2105.11904/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 35 references that are in the map.
- First posted on arXiv 12 May 2021.

## Builds on (most cited first, 22 of 22)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [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)
- [Going Deeper with Convolutions](https://mlsanity.com/paper/1409.4842/) (2014)
- [Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation](https://mlsanity.com/paper/1406.1078/) (2014)
- [Prototypical Networks for Few-shot Learning](https://mlsanity.com/paper/1703.05175/) (2017)
- [Deep contextualized word representations](https://mlsanity.com/paper/1802.05365/) (2018)
- [Matching Networks for One Shot Learning](https://mlsanity.com/paper/1606.04080/) (2016)
- [Learning to Compare: Relation Network for Few-Shot Learning](https://mlsanity.com/paper/1711.06025/) (2017)
- [A Closer Look at Few-shot Classification](https://mlsanity.com/paper/1904.04232/) (2019)
- [Few-Shot Learning with Graph Neural Networks](https://mlsanity.com/paper/1711.04043/) (2017)
- [A Baseline for Few-Shot Image Classification](https://mlsanity.com/paper/1909.02729/) (2019)
- [Meta Networks](https://mlsanity.com/paper/1703.00837/) (2017)
- [Meta-Learning: A Survey](https://mlsanity.com/paper/1810.03548/) (2018)
- [FewRel: A Large-Scale Supervised Few-Shot Relation Classification Dataset with State-of-the-Art Evaluation](https://mlsanity.com/paper/1810.10147/) (2018)
- [Bayesian Model-Agnostic Meta-Learning](https://mlsanity.com/paper/1806.03836/) (2018)
- [FewRel 2.0: Towards More Challenging Few-Shot Relation Classification](https://mlsanity.com/paper/1910.07124/) (2019)
- [Meta-Learning of Neural Architectures for Few-Shot Learning](https://mlsanity.com/paper/1911.11090/) (2019)
- [Diversity with Cooperation: Ensemble Methods for Few-Shot Classification](https://mlsanity.com/paper/1903.11341/) (2019)
- [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)
- [Ensemble Neural Relation Extraction with Adaptive Boosting](https://mlsanity.com/paper/1801.09334/) (2018)

## Built on by (most cited first, 4 of 4)

- [A SAM-guided Two-stream Lightweight Model for Anomaly Detection](https://mlsanity.com/paper/2402.19145/) (2024)
- [DPStyler: Dynamic PromptStyler for Source-Free Domain Generalization](https://mlsanity.com/paper/2403.16697/) (2024)
- [Generalizable Metric Network for Cross-domain Person Re-identification](https://mlsanity.com/paper/2306.11991/) (2023)
- [Bayesian adaptively-weighted ensembles for few-shot abdominal segmentation](https://mlsanity.com/paper/2608.05815/) (2026)

## Abstract (arXiv)

Few-shot learning has been proposed and rapidly emerging as a viable means for completing various tasks. Many few-shot models have been widely used for relation learning tasks. However, each of these models has a shortage of capturing a certain aspect of semantic features, for example, CNN on long-range dependencies part, Transformer on local features. It is difficult for a single model to adapt to various relation learning, which results in the high variance problem. Ensemble strategy could be competitive on improving the accuracy of few-shot relation extraction and mitigating high variance risks. This paper explores an ensemble approach to reduce the variance and introduces fine-tuning and feature attention strategies to calibrate relation-level features. Results on several few-shot relation learning tasks show that our model significantly outperforms the previous state-of-the-art models.