TY  - JOUR
T1  - Effective Importance-Based Entity Grouping Method in Continual Graph Embedding
AU  - Lee, Kyung-Hwan 
AU  - Choi, Dong-Wan 
JO  - Journal of KIISE, JOK
PY  - 2025
DA  - 2025/1/14
DO  - 10.5626/JOK.2025.52.7.627
KW  - continual learning
KW  - graph embedding
KW  - entity importance
KW  - betweenness centrality
KW  - weighted PageRank
KW  - network learning
AB  - This study proposed a novel approach to improving entity importance evaluation in continual graph embeddings by incorporating edge betweenness centrality as a weighting factor in a Weighted PageRank algorithm. By normalizing and integrating betweenness centrality, the proposed method effectively propagated entity importance while accounting for the significance of information flow through edges. Experimental results demonstrated significant performance improvements in MRR and Hit@N metrics across various datasets using the proposed method compared to existing methods. Notably, the proposed method showed enhanced learning performance after the initial snapshot in scenarios where new entities and relationships were continuously added. These findings highlight the effectiveness of leveraging edge centrality in promoting efficient and accurate learning in continual knowledge graph embeddings.