<![CDATA[This study examines the global development of learning transfer research through a bibliometric analysis of Scopus-indexed publications from 2000 to 2025. Using VOSviewer, the analysis maps keyword co-occurrences, thematic clusters, and intellectual linkages to reveal how learning transfer has evolved into a central paradigm within modern artificial intelligence. The findings show that research is dominated by four interconnected clusters: foundational deep learning concepts, computer vision applications, methodological advancements in transfer learning and domain adaptation, and emerging system-level applications such as reinforcement learning and federated learning. The prominence of terms like contrastive learning, fine tuning, and knowledge transfer highlights a shift toward more sophisticated, data-efficient, and privacy-conscious approaches. The dense interconnections among clusters demonstrate the field’s strong interdisciplinary nature, driven by collaborations across machine learning, cognitive science, and engineering. This study provides a comprehensive picture of the intellectual structure and emerging trajectories in learning transfer research, offering valuable insights for scholars, practitioners, and policymakers seeking to advance both theoretical foundations and practical applications.]]>
Copyrights © 2025
