Multi-view Feature Extraction based on Dual Contrastive Head
This work addresses dimensionality reduction in multi-view data for machine learning applications, representing an incremental improvement by integrating structural-level contrast into existing contrastive learning frameworks.
The paper tackles the problem of high-dimensional multi-view data by proposing a dual contrastive head method that combines structural-level and sample-level contrastive learning to extract more discriminative features, with experiments on six real datasets showing superior performance over existing methods.
Multi-view feature extraction is an efficient approach for alleviating the issue of dimensionality in highdimensional multi-view data. Contrastive learning (CL), which is a popular self-supervised learning method, has recently attracted considerable attention. Most CL-based methods were constructed only from the sample level. In this study, we propose a novel multiview feature extraction method based on dual contrastive head, which introduce structural-level contrastive loss into sample-level CL-based method. Structural-level CL push the potential subspace structures consistent in any two cross views, which assists sample-level CL to extract discriminative features more effectively. Furthermore, it is proven that the relationships between structural-level CL and mutual information and probabilistic intraand inter-scatter, which provides the theoretical support for the excellent performance. Finally, numerical experiments on six real datasets demonstrate the superior performance of the proposed method compared to existing methods.