GeCC: Generalized Contrastive Clustering with Domain Shifts Modeling
Yujie Chen, Wenhui Wu, Le Ou-Yang, Ran Wang, Debby D. Wang
Abstract
Contrastive clustering performs clustering and data representation in a unified model, where instance- and cluster-level constrastive learning are conducted simultaneously. However, commonly-used data augmentation methods make contrastive mechanism effect but may cause representation learning getting stuck in domain-specific information, which further deteriorates clustering performance and limits generalization ability. To this end, we propose a new framework, named Generalized Contrastive Clustering with domain shifts modeling (GeCC), which can integrate diverse domain knowledge to improve the clustering performance. Specifically, we first design a cluster-guided domain shifts modeling module to synthesize a reference view with diverse domain information. Then, we introduce instance representation and cluster assignment contrastive modules with well-designed attention weights to guide the representation learning and clustering. In this way, our method can maximize the extraction of cluster-related information and avoid over-fitting domain-specific features. Experimental results on four benchmark datasets demonstrate that our proposed method consistently outperforms other state-of-the-art methods.
BibTeX
@article{Chen_Wu_Ou-Yang_Wang_Wang_2025, title={GeCC: Generalized Contrastive Clustering with Domain Shifts Modeling}, volume={39}, url={https://ojs.aaai.org/index.php/AAAI/article/view/33753}, DOI={10.1609/aaai.v39i15.33753}, abstractNote={Contrastive clustering performs clustering and data representation in a unified model, where instance- and cluster-level constrastive learning are conducted simultaneously. However, commonly-used data augmentation methods make contrastive mechanism effect but may cause representation learning getting stuck in domain-specific information, which further deteriorates clustering performance and limits generalization ability. To this end, we propose a new framework, named Generalized Contrastive Clustering with domain shifts modeling (GeCC), which can integrate diverse domain knowledge to improve the clustering performance. Specifically, we first design a cluster-guided domain shifts modeling module to synthesize a reference view with diverse domain information. Then, we introduce instance representation and cluster assignment contrastive modules with well-designed attention weights to guide the representation learning and clustering. In this way, our method can maximize the extraction of cluster-related information and avoid over-fitting domain-specific features. Experimental results on four benchmark datasets demonstrate that our proposed method consistently outperforms other state-of-the-art methods.}, number={15}, journal={Proceedings of the AAAI Conference on Artificial Intelligence}, author={Chen, Yujie and Wu, Wenhui and Ou-Yang, Le and Wang, Ran and Wang, Debby D.}, year={2025}, month={Apr.}, pages={15966-15974} }