Markov Process-Based Graph Convolutional Networks for Entity Classification in Knowledge Graphs

2024-12-23

AI Summary

To address the degradation of graph convolutional network (GCN) performance caused by sparse entity class labels in knowledge graphs, this paper proposes MarkovGCN—a GCN framework integrated with Markov dynamics. Methodologically, entity classification is formulated as a state transition process, and Markovian dynamics are explicitly embedded into the GCN architecture for the first time. An adaptive propagation step sampling scheme based on the geometric distribution eliminates the need for manually specifying fixed layer depths. Furthermore, a joint loss function grounded in evidential learning is introduced to enhance uncertainty quantification. Extensive experiments on multiple benchmark datasets demonstrate that MarkovGCN consistently outperforms state-of-the-art GCN variants, achieving superior trade-offs between classification accuracy and computational efficiency. Crucially, its expected propagation depth is controllable via a hyperparameter, enabling flexible, application-aware balancing of model performance and inference cost.

Technology Category

• Machine Learning: Graph-based Machine Learning
• Reasoning under Uncertainty: Graphical Models
• Data Mining & Knowledge Management: Graph Mining, Social Network Analysis & Community

Application Category

• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Economics, Online Markets and Human Computation: Social networks and social learning

Abstract

Despite the vast amount of information encoded in Knowledge Graphs (KGs), information about the class affiliation of entities remains often incomplete. Graph Convolutional Networks (GCNs) have been shown to be effective predictors of complete information about the class affiliation of entities in KGs. However, these models do not learn the class affiliation of entities in KGs incorporating the complexity of the task, which negatively affects the models prediction capabilities. To address this problem, we introduce a Markov process-based architecture into well-known GCN architectures. This end-to-end network learns the prediction of class affiliation of entities in KGs within a Markov process. The number of computational steps is learned during training using a geometric distribution. At the same time, the loss function combines insights from the field of evidential learning. The experiments show a performance improvement over existing models in several studied architectures and datasets. Based on the chosen hyperparameters for the geometric distribution, the expected number of computation steps can be adjusted to improve efficiency and accuracy during training.

Problem

• Knowledge Graphs
• Graph Convolutional Networks
• Entity Classification

Innovation

• Markov Process Enhanced GCNs
• Entity Classification
• Dynamic Depth Learning