DICNet: Deep Instance-Level Contrastive Network for Double Incomplete Multi-View Multi-Label Classification
This addresses a practical challenge in real-world data analysis for researchers and practitioners dealing with incomplete multi-view multi-label data, though it appears incremental as it builds on existing contrastive learning and multi-view fusion techniques.
The paper tackles the problem of double incomplete multi-view multi-label classification, where both features and labels are often missing, by proposing DICNet, a deep instance-level contrastive network that learns high-level semantic representations. The result shows that DICNet outperforms state-of-the-art methods in experiments on five datasets.
In recent years, multi-view multi-label learning has aroused extensive research enthusiasm. However, multi-view multi-label data in the real world is commonly incomplete due to the uncertain factors of data collection and manual annotation, which means that not only multi-view features are often missing, and label completeness is also difficult to be satisfied. To deal with the double incomplete multi-view multi-label classification problem, we propose a deep instance-level contrastive network, namely DICNet. Different from conventional methods, our DICNet focuses on leveraging deep neural network to exploit the high-level semantic representations of samples rather than shallow-level features. First, we utilize the stacked autoencoders to build an end-to-end multi-view feature extraction framework to learn the view-specific representations of samples. Furthermore, in order to improve the consensus representation ability, we introduce an incomplete instance-level contrastive learning scheme to guide the encoders to better extract the consensus information of multiple views and use a multi-view weighted fusion module to enhance the discrimination of semantic features. Overall, our DICNet is adept in capturing consistent discriminative representations of multi-view multi-label data and avoiding the negative effects of missing views and missing labels. Extensive experiments performed on five datasets validate that our method outperforms other state-of-the-art methods.