Automatic Similarity Feature Combination for Knowledge Graph Alignment via Adaptive-Designed Particle Swarm Optimization With Genetic Programming

Knowledge Graphs (KGs) enable structured representation of domain-specific knowledge, but their integration is challenged by ontology heterogeneity due to varying terminologies and levels of granularity. KG alignment addresses this issue by identifying correspondences between semantically similar entities across diverse KGs, relying heavily on the effective combination of Similarity Features (SFs). However, manually determining the optimal combination of SFs is inefficient and often inaccurate, especially given the complex interactions among entities in different domains. To address this problem, this paper develops an Adaptive-Designed Particle Swarm Optimization (ADPSO) to automate SF combination for KG alignment. First, an adaptive framework is developed to dynamically adjust solution movement and evaluation rules, mitigating premature convergence. Second, a novel evaluation rule construction method is proposed, leveraging Genetic Programming (GP) to refine the fitness function, enhancing solution evaluation accuracy. Finally, a new velocity update mechanism is designed using a success update archive and GP, improving search efficiency. Experiments on diverse KG alignment tasks demonstrate that ADPSO significantly enhances matching accuracy and efficiency, achieving superior performance compared to state-of-the-art methods with an average f-measure of 0.90.