Learn from Relation Information: Towards Prototype Representation Rectification for Few-Shot Relation Extraction

2022-07-01 · Findings (NAACL) 2022 7 · Yang Liu, Jinpeng Hu, Xiang Wan, Tsung-Hui Chang

Few-shot Relation Extraction refers to fast adaptation to novel relation classes with few samples through training on the known relation classes. Most existing methods focus on implicitly introducing relation information (i.e., relation label or relation description) to constrain the prototype representation learning, such as contrastive learning, graphs, and specifically designed attentions, which may bring useless and even harmful parameters. Besides, these approaches are limited in handing outlier samples far away from the class center due to the weakly implicit constraint. In this paper, we propose an effective and parameter-less Prototype Rectification Method (PRM) to promote few-shot relation extraction, where we utilize a prototype rectification module to rectify original prototypes explicitly by the relation information. Specifically, PRM is composed of two gate mechanisms. One gate decides how much of the original prototype remains, and another one updates the remained prototype with relation information. In doing so, better and stabler global relation information can be captured for guiding prototype representations, and thus PRM can robustly deal with outliers. Moreover, we also extend PRM to both none-of-the-above (NOTA) and domain adaptation scenarios. Experimental results on FewRel 1.0 and 2.0 datasets demonstrate the effectiveness of our proposed method, which achieves state-of-the-art performance.

📄 PDF Abstract BibTeX

Code (1)

lylylylylyly/prm-fsre 공식 구현 pytorch

Tasks

Contrastive Learning Domain AdaptationRelationRelation Extraction Representation Learning

Addressing Skewed Heterogeneity via Federated Prototype Rectification with Personalization

2024-08-15 · Shunxin Guo, Hongsong Wang, Shuxia Lin, Zhiqiang Kou 외

Federated learning is an efficient framework designed to facilitate collaborative model training across multiple distributed devices while preserving user data privacy. A significant challenge of federated learning is da…

Federated Learning

Leveraging Labelled Data Knowledge: A Cooperative Rectification Learning Network for Semi-supervised 3D Medical Image Segmentation

2025-02-17 · Yanyan Wang, Kechen Song, Yuyuan Liu, Shuai Ma 외

Semi-supervised 3D medical image segmentation aims to achieve accurate segmentation using few labelled data and numerous unlabelled data. The main challenge in the design of semi-supervised learning methods consists in t…

Image Segmentation Medical Image Segmentation Pseudo Label Segmentation+1

Prototype Rectification for Few-Shot Learning

2019-11-25 · ECCV 2020 8 · Jinlu Liu, Liang Song, Yongqiang Qin

Few-shot learning requires to recognize novel classes with scarce labeled data. Prototypical network is useful in existing researches, however, training on narrow-size distribution of scarce data usually tends to get bia…

Few-Shot Image Classification Few-Shot Learning

Conditional Prototype Rectification Prompt Learning

2024-04-15 · Haoxing Chen, Yaohui Li, Zizheng Huang, Yan Hong 외

Pre-trained large-scale vision-language models (VLMs) have acquired profound understanding of general visual concepts. Recent advancements in efficient transfer learning (ETL) have shown remarkable success in fine-tuning…

Few-Shot Learning Prompt Learning Transfer Learning

RAPS: A Novel Few-Shot Relation Extraction Pipeline with Query-Information Guided Attention and Adaptive Prototype Fusion

2022-10-15 · Yuzhe Zhang, Min Cen, Tongzhou Wu, Hong Zhang

Few-shot relation extraction (FSRE) aims at recognizing unseen relations by learning with merely a handful of annotated instances. To generalize to new relations more effectively, this paper proposes a novel pipeline for…

Relation Relation Extraction