mlsanityData to 14 Oct 2026

Mere Contrastive Learning for Cross-Domain Sentiment Analysis

arXiv 2208.08678 ↗First posted 18 Aug 2022cs.CL cs.AIcited by 8

Not on the map. Why?

Abstract (arXiv)

Cross-domain sentiment analysis aims to predict the sentiment of texts in the target domain using the model trained on the source domain to cope with the scarcity of labeled data. Previous studies are mostly cross-entropy-based methods for the task, which suffer from instability and poor generalization. In this paper, we explore contrastive learning on the cross-domain sentiment analysis task. We propose a modified contrastive objective with in-batch negative samples so that the sentence representations from the same class will be pushed close while those from the different classes become further apart in the latent space. Experiments on two widely used datasets show that our model can achieve state-of-the-art performance in both cross-domain and multi-domain sentiment analysis tasks. Meanwhile, visualizations demonstrate the effectiveness of transferring knowledge learned in the source domain to the target domain and the adversarial test verifies the robustness of our model.

Key facts. Cited by 8 papers in the map (data through 14 Oct 2026). Builds on 28 of its 47 references that are in the map. First posted on arXiv 18 Aug 2022.

Builds on

28 of 47 references.

References · 28

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  2. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  3. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  4. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 12,049
  5. 2019BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehensioncited by 5,893
  6. 2021Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervisioncited by 3,864
  7. 2020Supervised Contrastive Learningcited by 2,829
  8. 2021SimCSE: Simple Contrastive Learning of Sentence Embeddingscited by 2,173
  9. 2020Understanding Contrastive Representation Learning through Alignment and Uniformity on the Hyperspherecited by 1,405
  10. 2018Generalized Cross Entropy Loss for Training Deep Neural Networks with Noisy Labelscited by 997
  11. 2019Learning Imbalanced Datasets with Label-Distribution-Aware Margin Losscited by 989
  12. 2019Is BERT Really Robust? A Strong Baseline for Natural Language Attack on Text Classification and Entailmentcited by 671
16 more
  1. 2020Fine-Tuning Pretrained Language Models: Weight Initializations, Data Orders, and Early Stoppingcited by 384
  2. 2021Understanding Dimensional Collapse in Contrastive Self-supervised Learningcited by 378
  3. 2022Text and Code Embeddings by Contrastive Pre-Trainingcited by 361
  4. 2016Large-Margin Softmax Loss for Convolutional Neural Networkscited by 296
  5. 2020Supervised Contrastive Learning for Pre-trained Language Model Fine-tuningcited by 276
  6. 2019Representation Degeneration Problem in Training Natural Language Generation Modelscited by 255
  7. 2020Revisiting Few-sample BERT Fine-tuningcited by 238
  8. 2020Nearest Neighbor Machine Translationcited by 209
  9. 2020Towards Discriminability and Diversity: Batch Nuclear-norm Maximization under Label Insufficient Situationscited by 133
  10. 2018Large Margin Deep Networks for Classificationcited by 112
  11. 2017Adversarial Multi-task Learning for Text Classificationcited by 91
  12. 2019Cross-Entropy Loss and Low-Rank Features Have Responsibility for Adversarial Examplescited by 17
  13. 2021A Relation-Oriented Clustering Method for Open Relation Extractioncited by 15
  14. 2018Same Representation, Different Attentions: Shareable Sentence Representation Learning from Multiple Taskscited by 9
  15. 2021KNN-BERT: Fine-Tuning Pre-Trained Models with KNN Classifiercited by 7
  16. 2019Learning Word Embeddings with Domain Awarenesscited by 1

Built on by

Cited by year

Citing papers per year: 2022: 2; 2023: 3; 2024: 1; 2025: 2.

8 papers.

  1. 2023Improving (Dis)agreement Detection with Inductive Social Relation Information From Comment-Reply Interactionscited by 5
  2. 2023Mitigating Catastrophic Forgetting in Task-Incremental Continual Learning with Adaptive Classification Criterioncited by 4
  3. 2022Semantic-based Pre-training for Dialogue Understandingcited by 3
  4. 2024Domain Generalization via Causal Adjustment for Cross-Domain Sentiment Analysiscited by 3
  5. 2022A Curriculum Learning Approach for Multi-domain Text Classification Using Keyword weight Rankingcited by 2
  6. 2023Enhancing Argument Structure Extraction with Efficient Leverage of Contextual Informationcited by 1
  7. 2025Signs of Struggle: Spotting Cognitive Distortions across Language and Registercited by 0
  8. 2025BanglaSentNet: An Explainable Hybrid Deep Learning Framework for Multi-Aspect Sentiment Analysis with Cross-Domain Transfer Learningcited by 0