Yujia Zhang, Tyler Sadler, Mohammad Reza Taesiri, Wenjie Xu, Marek Reformat. Proceedings of the 1st Workshop on Knowledge Graphs and Large Language Models (KaLLM 2024). 2024.
Hierarchy analysis of the knowledge graphs aims to discover the latent structure inherent in knowledge base data. Drawing inspiration from topic modeling, which identifies latent themes and content patterns in text corpora, our research seeks to adapt these analytical frameworks to the hierarchical exploration of knowledge graphs. Specifically, we adopt a non-parametric probabilistic model, the nested hierarchical Dirichlet process, to the field of knowledge graphs. This model discovers latent subject-specific distributions along paths within the tree. Consequently, the global tree can be viewed as a collection of local subtrees for each subject, allowing us to represent subtrees for each subject and reveal cross-thematic topics. We assess the efficacy of this model in analyzing the topics and word distributions that form the hierarchical structure of complex knowledge graphs. We quantitatively evaluate our model using four common datasets: Freebase, Wikidata, DBpedia, and WebRED, demonstrating that it outperforms the latest neural hierarchical clustering techniques such as TraCo, SawETM, and HyperMiner. Additionally, we provide a qualitative assessment of the induced subtree for a single subject.
2 July 2026 in Nonlinear Analysis and Computer Simulations
The reliability of the power supply is intrinsically linked to the robustness of the distribution network. Constructing a distribution network model is highly challenging due to its complex structure, the large number of equipment and users, and the randomness of load variations and equipment failures. Knowledge graphs, a structured data representation describing entities and their relationships, can address challenges by modelling various devices, users and real-time operation data as entities in a graphical manner. As a result, the constructed large network graphs are not only easy to interpret, but also efficient in data management and reliability analysis. The results are promising and validate our hypothesis.