# Cross-Domain Sentiment Classification with Contrastive Learning and Mutual Information Maximization

arXiv: https://arxiv.org/abs/2010.16088 · HTML: https://mlsanity.com/paper/2010.16088/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 30 Oct 2020.

## Built on by (most cited first, 9 of 9)

- [Enhancing Out-of-Distribution Detection in Natural Language Understanding via Implicit Layer Ensemble](https://mlsanity.com/paper/2210.11034/) (2022)
- [One-Versus-Others Attention: Scalable Multimodal Integration for Biomedical Data](https://mlsanity.com/paper/2307.05435/) (2023)
- [Domain-Adaptive Text Classification with Structured Knowledge from Unlabeled Data](https://mlsanity.com/paper/2206.09591/) (2022)
- [Probing Out-of-Distribution Robustness of Language Models with Parameter-Efficient Transfer Learning](https://mlsanity.com/paper/2301.11660/) (2023)
- [Universal Domain Adaptation for Robust Handling of Distributional Shifts in NLP](https://mlsanity.com/paper/2310.14849/) (2023)
- [Bi-Granularity Contrastive Learning for Post-Training in Few-Shot Scene](https://mlsanity.com/paper/2106.02327/) (2021)
- [A Simple Information-Based Approach to Unsupervised Domain-Adaptive Aspect-Based Sentiment Analysis](https://mlsanity.com/paper/2201.12549/) (2022)
- [Supervised Graph Contrastive Pretraining for Text Classification](https://mlsanity.com/paper/2112.11389/) (2021)
- [BanglaSentNet: An Explainable Hybrid Deep Learning Framework for Multi-Aspect Sentiment Analysis with Cross-Domain Transfer Learning](https://mlsanity.com/paper/2511.23264/) (2025)

## Abstract (arXiv)

Contrastive learning (CL) has been successful as a powerful representation learning method. In this work we propose CLIM: Contrastive Learning with mutual Information Maximization, to explore the potential of CL on cross-domain sentiment classification. To the best of our knowledge, CLIM is the first to adopt contrastive learning for natural language processing (NLP) tasks across domains. Due to scarcity of labels on the target domain, we introduce mutual information maximization (MIM) apart from CL to exploit the features that best support the final prediction. Furthermore, MIM is able to maintain a relatively balanced distribution of the model's prediction, and enlarges the margin between classes on the target domain. The larger margin increases our model's robustness and enables the same classifier to be optimal across domains. Consequently, we achieve new state-of-the-art results on the Amazon-review dataset as well as the airlines dataset, showing the efficacy of our proposed method CLIM.