mlsanityData to 7 Oct 2026

ContrastNet: A Contrastive Learning Framework for Few-Shot Text Classification

arXiv 2305.09269 ↗First posted 16 May 2023cs.CLcited by 17

Not on the map. Why?

Abstract (arXiv)

Few-shot text classification has recently been promoted by the meta-learning paradigm which aims to identify target classes with knowledge transferred from source classes with sets of small tasks named episodes. Despite their success, existing works building their meta-learner based on Prototypical Networks are unsatisfactory in learning discriminative text representations between similar classes, which may lead to contradictions during label prediction. In addition, the tasklevel and instance-level overfitting problems in few-shot text classification caused by a few training examples are not sufficiently tackled. In this work, we propose a contrastive learning framework named ContrastNet to tackle both discriminative representation and overfitting problems in few-shot text classification. ContrastNet learns to pull closer text representations belonging to the same class and push away text representations belonging to different classes, while simultaneously introducing unsupervised contrastive regularization at both task-level and instance-level to prevent overfitting. Experiments on 8 few-shot text classification datasets show that ContrastNet outperforms the current state-of-the-art models.

Key facts. Cited by 17 papers in the map (data through 7 Oct 2026). Builds on 30 of its 38 references that are in the map. First posted on arXiv 16 May 2023.

Builds on

30 of 38 references.

References · 30

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 11,979
  3. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,861
  4. 2017Prototypical Networks for Few-shot Learningcited by 3,001
  5. 2020Supervised Contrastive Learningcited by 2,803
  6. 2016Matching Networks for One Shot Learningcited by 2,246
  7. 2021SimCSE: Simple Contrastive Learning of Sentence Embeddingscited by 2,168
  8. 2020Graph Contrastive Learning with Augmentationscited by 1,203
  9. 2017Learning to Compare: Relation Network for Few-Shot Learningcited by 1,139
  10. 2020What Makes for Good Views for Contrastive Learning?cited by 843
  11. 2019EDA: Easy Data Augmentation Techniques for Boosting Performance on Text Classification Taskscited by 800
  12. 2016Ups and Downs: Modeling the Visual Evolution of Fashion Trends with One-Class Collaborative Filteringcited by 517
18 more
  1. 2020Efficient Intent Detection with Dual Sentence Encoderscited by 419
  2. 2020Hard Negative Mixing for Contrastive Learningcited by 399
  3. 2019Cross Attention Network for Few-shot Classificationcited by 218
  4. 2020Cross-Domain Few-Shot Classification via Learned Feature-Wise Transformationcited by 183
  5. 2019Benchmarking Natural Language Understanding Services for building Conversational Agentscited by 166
  6. 2021Free Lunch for Few-shot Learning: Distribution Calibrationcited by 165
  7. 2020DialoGLUE: A Natural Language Understanding Benchmark for Task-Oriented Dialoguecited by 89
  8. 2019Induction Networks for Few-Shot Text Classificationcited by 64
  9. 2018Diverse Few-Shot Text Classification with Multiple Metricscited by 61
  10. 2019Few-shot Text Classification with Distributional Signaturescited by 58
  11. 2019Learning to Few-Shot Learn Across Diverse Natural Language Classification Taskscited by 57
  12. 2020Joint Contrastive Learning with Infinite Possibilitiescited by 31
  13. 2020Dynamic Memory Induction Networks for Few-Shot Text Classificationcited by 23
  14. 2021ProtAugment: Unsupervised diverse short-texts paraphrasing for intent detection meta-learningcited by 18
  15. 2021Meta-Learning Adversarial Domain Adaptation Network for Few-Shot Text Classificationcited by 18
  16. 2021Contrastive Prototype Learning with Augmented Embeddings for Few-Shot Learningcited by 15
  17. 2021Boosting Few-Shot Classification with View-Learnable Contrastive Learningcited by 11
  18. 2021Multi-Level Contrastive Learning for Few-Shot Problemscited by 1

Built on by

Cited by year

Citing papers per year: 2023: 7; 2024: 10.

17 papers.

Sort:

By area:

  1. 2023ConDA: Contrastive Domain Adaptation for AI-generated Text Detectioncited by 37
  2. 2024Heterogeneous Contrastive Learning for Foundation Models and Beyondcited by 27
  3. 2024Distractor Generation in Multiple-Choice Tasks: A Survey of Methods, Datasets, and Evaluationcited by 25
  4. 2024Retrieval-style In-Context Learning for Few-shot Hierarchical Text Classificationcited by 16
  5. 2023Effective Structured Prompting by Meta-Learning and Representative Verbalizercited by 14
  6. 2024Is Contrasting All You Need? Contrastive Learning for the Detection and Attribution of AI-generated Textcited by 11
  7. 2024Mitigating Boundary Ambiguity and Inherent Bias for Text Classification in the Era of Large Language Modelscited by 9
  8. 2023Pre-training Intent-Aware Encoders for Zero- and Few-Shot Intent Classificationcited by 5
  9. 2023BYOC: Personalized Few-Shot Classification with Co-Authored Class Descriptionscited by 5
  10. 2024Across-Game Engagement Modelling via Few-Shot Learningcited by 4
  11. 2023TART: Improved Few-shot Text Classification Using Task-Adaptive Reference Transformationcited by 3
  12. 2024Learning Label Hierarchy with Supervised Contrastive Learningcited by 3
5 more
  1. 2024GANs Conditioning Methods: A Surveycited by 3
  2. 2023DRAFT: Dense Retrieval Augmented Few-shot Topic classifier Frameworkcited by 1
  3. 2023TK-KNN: A Balanced Distance-Based Pseudo Labeling Approach for Semi-Supervised Intent Classificationcited by 0
  4. 2024Visual Analytics for Fine-grained Text Classification Models and Datasetscited by 0
  5. 2024Improve Meta-learning for Few-Shot Text Classification with All You Can Acquire from the Taskscited by 0