Uncertainty-Aware Global-View Reconstruction for Multi-View Multi-Label Feature Selection

2025-03-18

AI Summary

To address the insufficient coupling between feature selection and sample uncertainty modeling in multi-view multi-label learning (MVML), this paper proposes a global view reconstruction-based, uncertainty-aware unified framework. The method innovatively embeds sample confidence into the view reconstruction process, jointly modeling sample graph structure, inter-view consistency, and complementarity. It achieves end-to-end optimization via graph neural networks, label matrix alignment, and sparsity regularization. Key contributions include: (i) an uncertainty-driven joint reconstruction mechanism that explicitly incorporates sample confidence during reconstruction; and (ii) a unified integration of consistency and complementarity information—avoiding noise introduced by heuristic, disjoint modeling. Extensive experiments on multiple benchmark datasets demonstrate significant improvements in classification accuracy and generalization performance, with feature compression exceeding 30% and superior robustness over existing state-of-the-art methods.

Technology Category

• Machine Learning: Multi-instance/Multi-view Learning
• Computer Vision: Multi-modal Vision
• Reasoning under Uncertainty: Uncertainty Representations

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

In recent years, multi-view multi-label learning (MVML) has gained popularity due to its close resemblance to real-world scenarios. However, the challenge of selecting informative features to ensure both performance and efficiency remains a significant question in MVML. Existing methods often extract information separately from the consistency part and the complementary part, which may result in noise due to unclear segmentation. In this paper, we propose a unified model constructed from the perspective of global-view reconstruction. Additionally, while feature selection methods can discern the importance of features, they typically overlook the uncertainty of samples, which is prevalent in realistic scenarios. To address this, we incorporate the perception of sample uncertainty during the reconstruction process to enhance trustworthiness. Thus, the global-view is reconstructed through the graph structure between samples, sample confidence, and the view relationship. The accurate mapping is established between the reconstructed view and the label matrix. Experimental results demonstrate the superior performance of our method on multi-view datasets.

Problem

• Selecting informative features in multi-view multi-label learning.
• Addressing uncertainty of samples during feature reconstruction.
• Improving trustworthiness through global-view reconstruction and sample confidence.

Innovation

• Unified global-view reconstruction model
• Incorporates sample uncertainty perception
• Graph-based view and label mapping