Adversarial Graph Fusion for Incomplete Multi-view Semi-supervised Learning with Tensorial Imputation

2025-09-19

AI Summary

In multi-view semi-supervised learning, view incompleteness induces sub-cluster fragmentation, violating the graph structural continuity and label propagation smoothness assumptions—thereby degrading graph fusion efficacy and classification performance. This work is the first to systematically characterize this detrimental impact on graph fusion. We propose a novel framework integrating adversarial graph fusion with anchor-guided low-rank tensor completion: adversarial fusion models cross-view higher-order consistency to enhance local structural robustness, while tensor completion recovers missing views under low-rank constraints to preserve graph integrity. The method synergistically combines adversarial optimization, low-rank tensor learning, and simplified gradient descent—ensuring both computational efficiency and guaranteed convergence. Extensive experiments on multiple benchmark datasets demonstrate significant improvements in classification accuracy and graph structure recovery quality, validating the method’s effectiveness, stability, and superiority over state-of-the-art approaches.

Technology Category

• Machine Learning: Multi-instance/Multi-view Learning
• Computer Vision: Adversarial Attacks & Robustness
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• Graph Algorithms and Modeling for the Web: Graph embeddings and representation learning for Web-related graphs
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

View missing remains a significant challenge in graph-based multi-view semi-supervised learning, hindering their real-world applications. To address this issue, traditional methods introduce a missing indicator matrix and focus on mining partial structure among existing samples in each view for label propagation (LP). However, we argue that these disregarded missing samples sometimes induce discontinuous local structures, i.e., sub-clusters, breaking the fundamental smoothness assumption in LP. Consequently, such a Sub-Cluster Problem (SCP) would distort graph fusion and degrade classification performance. To alleviate SCP, we propose a novel incomplete multi-view semi-supervised learning method, termed AGF-TI. Firstly, we design an adversarial graph fusion scheme to learn a robust consensus graph against the distorted local structure through a min-max framework. By stacking all similarity matrices into a tensor, we further recover the incomplete structure from the high-order consistency information based on the low-rank tensor learning. Additionally, the anchor-based strategy is incorporated to reduce the computational complexity. An efficient alternative optimization algorithm combining a reduced gradient descent method is developed to solve the formulated objective, with theoretical convergence. Extensive experimental results on various datasets validate the superiority of our proposed AGF-TI as compared to state-of-the-art methods. Code is available at https://github.com/ZhangqiJiang07/AGF_TI.

Problem

• Addresses incomplete multi-view semi-supervised learning challenges
• Solves sub-cluster problem from missing samples in graphs
• Recovers incomplete structures through adversarial tensor fusion

Innovation

• Adversarial graph fusion for robust consensus
• Tensor imputation for high-order structure recovery
• Anchor-based strategy to reduce computational complexity