A Novel Compressed Sensing-Based Graph Isomorphic Network for Key Node Recognition and Entity Alignment

Abstract

In recent years, the related research of entity alignment has mainly focused on entity alignment via knowledge embeddings and graph neural networks; however, these proposed models usually suffer from structural heterogeneity and the large-scale problem of knowledge graph. A novel entity alignment model based on graph isomorphic network and compressed sensing is proposed. First, for the problem of structural heterogeneity, graph isomorphic network encoder is applied in knowledge graph to capture structural similarity of entity relation. Second, for the problem of large scale, key node and community are integrated for priority entity alignment to improve execution speed. However, the exiting node importance ranking algorithm cannot accurately identify key node in knowledge graph. So the compressed sensing is adopted in node importance ranking to improve the accuracy of identifying key node. The authors have carried out several experiments to test the effect and efficiency of the proposed entity alignment model.

A Semantically Enhanced Knowledge Discovery Method for Knowledge Graph Based on Adjacency Fuzzy Predicates Reasoning

“…Some of studies apply knowledge graph to the construction and security of social networks (Zhang & Gupta, 2018;Zhang et al, 2017), while others focus on knowledge graph-based personalized recommendations (Casillo et al, 2022) and intelligent Q&A (Do, Phan, & Gupta, 2021). Besides, some new knowledge graph reasoning methods adopt different reasoning strategies, such as embedding-based reasoning task (Lin et al, 2021), reasoning-based recommendation system (Chen, Yu, Lu, Qian, & Li, 2021), and sensing-based entity recognition and alignment (Zhao, Huang, Fan, Wu, & Liu, 2022). Most notably, there are some new researches on fuzzy semantics of knowledge graph.…”

A Web Semantic-Based Text Analysis Approach for Enhancing Named Entity Recognition Using PU-Learning and Negative Sampling

“…NLP is a pivotal domain within deep learning and encompasses various developmental trajectories and applications (Ismail et al, 2022;Vats et al, 2023), such as text classification (Singh & Sachan, 2021;Miri et al, 2022), text-to-image synthesis (Chopra et al, 2022), and unsupervised information extraction (Sarkissian & Tekli, 2021;Hajjar & Tekli, 2022). Among these domains, knowledge graphs are an indispensable component and have extensive applications in various fields (Zhao et al, 2022;Zhou et al, 2022a;Li et al, 2023), such as health care and cybersecurity (Gou et al, 2017;Sahoo & Gupta, 2019). NER is a crucial task in knowledge graphs and has received significant attention.…”