MORI-RAN: Multi-view Robust Representation Learning via Hybrid Contrastive Fusion

作者：Guanzhou Ke, Yongqi Zhu, Yu Yang · 发表于：2022 IEEE International Conference on Data Mining Workshops (ICDMW) · 年份：2022 · DOI：10.1109/icdmw58026.2022.00068 · 被引用次数：11 · 研究领域：Domain Adaptation and Few-Shot Learning、Video Surveillance and Tracking Methods、Advanced Image and Video Retrieval Techniques

Multi-view representation learning is essential for many multi-view tasks, such as clustering and classification. However, there are two challenging problems plaguing the community: i)how to learn robust multi-view representations from mass unlabeled data and ii) how to balance the view consistency and specificity. To this end, in this paper, we proposed a novel hybrid contrastive fusion method to extract robust view-common representations from unlabeled data. Specifically, we found that introducing an additional representation space and aligning representations on this space enables the model to learn robust view-common representations. At the same time, we designed an asymmetric contrastive strategy to ensure that the model does not obtain trivial solutions. Experimental results demonstrated that the proposed method outperforms 12 competitive multi-view methods on four real-world datasets in terms of clustering and classification. Our source code will be available soon at httns:/ /github.com/guanzhou- ke/mori- ran.