This work proposes a semi-supervised generative model that utilizes both labeled and unlabeled samples in a unified framework and maximizes the likelihood of unlabeled samples to learn a latent space shared with the IB on labeled data.
Abstract
Multi-view learning is widely applied to real-life datasets, but it often suffers from both missing views and missing labels. Prior probabilistic approaches addressed the missing view problem by using a product-of-experts scheme to aggregate representations from present views and achieved superior performance over deterministic classifiers, using the information bottleneck (IB) principle. However, the IB framework is inherently fully supervised and cannot leverage unlabeled data. In this work, we propose a semi-supervised generative model that utilizes both labeled and unlabeled samples in a unified framework. Our method maximizes the likelihood of unlabeled samples to learn a latent space shared with the IB on labeled data. We also include modality-specific information in likelihood modeling and perform cross-view mutual information maximization in the shared latent space to enhance the extraction of shared information across views. Compared to existing approaches, our model achieves better predictive and generation performance on complex datasets with missing views and limited labeled samples.
This paper explicitly model and learn correlations between views by utilizing the covariance structure of posterior estimation errors during aggregation, demonstrating the need to go beyond the independence assumption in IMVC.
Zhe-Ming Xu, A. Tang, Shidi Chen et al.· 0 citations
A novel PML method, namely Wasserstein Partial Multi-Label Learning with dual Label Correlation Perspectives (Wpml3cp), solved by the gradient descent with an augmented Lagrange multiplier technique, and empirical results demonstrate that Wpml3cp and Wpml3cp-D can outperform the PML baselines in various noisy levels.
Xi-Ming Li, Yuanchao Dai, Bing Wang et al.· ACM Transactions on Knowledg...· 0 citations
This work proposes a Self-supervised Probability Distribution-driven Deep Incomplete Multi-view Clustering method (SPDIM), which first handles missing views at the data level, utilizing uncertainty-aware sampling to interpolate missing information and thereby enforce global consistency across samples.
Shengxia Gao, Wei-Yi Wei, Yongxin Shi et al.· Multimedia Systems· 0 citations
Gaussian-mixture calculations and a medical diagnosis example illustrate how uncertainty-dependent labeling mechanisms can improve estimation and classification under a fixed labeling budget.
You-Gan Wang, Jin-Ran Wu, Geoffrey J. McLachlan· 0 citations
Incomplete multi-view multi-label learning requires not only robust semantic aggregation from partially observed views, but also label-aware exploitation of view-specific evidence. Existing approaches usually emphasize either shared representation learning or decision-level fusion. The former improves robustness agains...
Chengliang Liu, Bo Li, Bob Zhang et al.· IEEE Transactions on Pattern...· 0 citations
Related blog posts
MIT News · Artificial Intelligence· news.mit.eduOct 13, 2026
Machine-learning networks can learn without detailed instructions from a designer. Those that do may offer insight into how the brain reorganizes itself during learning.
MIT News · Artificial Intelligence· news.mit.eduSep 29, 2026
Professor Sherry Turkle’s new book, “Artificial Intimacy,” offers a withering critique of chatbots and the antisocial dynamics she believes they encourage.