Bibliometric Analysis of Global Research Trends in Neural Networks and Graph Neural Networks

Neural Networks (NNs) and Graph Neural Networks (GNNs) represent two of the most rapidly expanding subfields in artificial intelligence, driving advances across pattern recognition, computer vision, natural language processing, and graph-structured learning. To understand the evolution and growth of these research domains, this study performs a comprehensive bibliometric analysis using publication records extracted from a dataset consisting of 47,194 documents spanning the years 2002 to 2025. The analysis examines publication trends, leading authors, affiliations, countries, publication venues, document types, editorial patterns, and open access characteristics. Findings reveal exponential growth from 2016 onward, a strong concentration of contributions from China, the United States, and leading global universities, and the dominance of IEEE, Elsevier, and Springer Nature as key publishers. The results highlight the maturity of neural network research and the rapidly rising status of GNNs as influential deep learning architectures. This bibliometric study provides a consolidated understanding of global research patterns and serves as a valuable reference for scholars, policymakers, and funding agencies.