Papers › Dual Contrastive Learning: Text Classification via Label-Aware Data Augmentation

Dual Contrastive Learning: Text Classification via Label-Aware Data Augmentation

21 Jan 2022arXiv:2201.08702archive 2025-07-28

Qianben Chen, Richong Zhang, Yaowei Zheng, Yongyi Mao

Contrastive learning has achieved remarkable success in representation learning via self-supervision in unsupervised settings. However, effectively adapting contrastive learning to supervised learning tasks remains as a challenge in practice. In this work, we introduce a dual contrastive learning (DualCL) framework that simultaneously learns the features of input samples and the parameters of classifiers in the same space. Specifically, DualCL regards the parameters of the classifiers as augmented samples associating to different labels and then exploits the contrastive learning between the input samples and the augmented samples. Empirical studies on five benchmark text classification datasets and their low-resource version demonstrate the improvement in classification accuracy and confirm the capability of learning discriminative representations of DualCL.

Paper PDF Code

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

hiyouga/dual-contrastive-learning officialmentioned in papermentioned on GitHubpytorch report

hiyouga/hiyouga mentioned on GitHubtfMIT report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Classification Contrastive Learning Data Augmentation Representation Learning Sentiment Analysis Subjectivity Analysis Text Classification text-classification

Results from the paper archive 2025-07-28

Task	Dataset	Model	Metric	Value	Rank at snapshot	Leaderboard	Report
Sentiment Analysis	SST-2 Binary classification	RoBERTa+DualCL	Accuracy	94.91	#26 of 87	Archive leaderboard	report
Subjectivity Analysis	SUBJ	RoBERTa+DualCL	Accuracy	97.34	#1 of 19	Archive leaderboard	report
Text Classification	TREC-6	RoBERTa+DualCL	Error	2.60	#3 of 19	Archive leaderboard	report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Introduced by this paper: DualCL

Adam Attention Attention Dropout BERT Contrastive Learning Dense Connections Dropout DualCL Layer Normalization Linear Layer Linear Warmup With Linear Decay Multi-Head Attention Residual Connection RoBERTa Softmax Weight Decay WordPiece

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections