20.500.12556/DKUM-97840 Enhancing graph summarization using node importance and graph attention networks As the scale of graph-structured data continues to grow, graph summarization has become an important technique for storage efficiency and high-level visualization. This study investigates a Node Importance (NI) approach to graph summarization that prioritizes structural integrity over simple size reduction. The NI approach selects super nodes by ranking vertices through centrality and propagation metrics. Experimental results demonstrate that the proposed NI method achieves compression rates comparable to or slightly lower than traditional Minimum Description Length (MDL) methods across various datasets while maintaining structural integrity. However, today, the high dimensionality and complexity of modern graph data are making deep learning techniques more popular. Great progress in deep learning summarization techniques is achieved with Graph Neural Networks (GNNs). This study investigates the structure and suitability of different GNN architectures for graph summarization using the NI approach. Graph Attention Networks (GATs) and their variants are discussed as a flexible, learned notion of node importance via attention. We present an examination of GATs, covering both diverse approaches and improvements. This study also discusses extensions that enhance the concept of node importance established by the GAT model, GAT variants for node importance estimation, and application-specific GAT research. graph summarization node importance graph neural networks graph attention networks povzemanje grafov pomembnost vozlišč grafovske nevronske mreže mreže pozornosti grafov true false true MDPI Angleški jezik Slovenski jezik https://www.mdpi.com/journal/mathematics Članek v reviji 2026-04-18 03:18:42 2026-05-08 09:19:42 2026-05-09 03:09:16 0000-00-00 00:00:00 2026 0 0 20 str. no. 8, [article no.] 1283 Vol. 14 2026 0000-00-00 Zaloznikova Objavljeno NiDoloceno 2026-03-02 2026-04-10 2026-04-12 004.8:004.62:519.17 275632131 10.3390/math14081283 2227-7390 mathematics-14-01283-v2.pdf mathematics-14-01283-v2.pdf 1 BE97B8DB34AC287AD3724A873D4D286B 8eb3566dc4422f42b71aa74ef9a506c2f9c114fea3bc1bf918c35e39af0dde87 f0df1fa3-4aad-11f1-a4b2-00155d0001a1 https://dk.um.si/Dokument.php?lang=slv&id=205918 https://www.mdpi.com/2227-7390/14/8/1283 0 e3e20bc9-4aad-11f1-a4b2-00155d0001a1 https://dk.um.si/Dokument.php?lang=slv&id=205917 https://doi.org/10.3390/math14081283 1 8a5b3fe6-3ac4-11f1-8e7a-00155d0001a1 https://dk.um.si/Dokument.php?lang=slv&id=205422 Fakulteta za elektrotehniko, računalništvo in informatiko 0 0 0