3 papers
cs.LG2026
Enhancing Distance-Based Graph Autoencoders with Structural Penalties for Dynamic Graph Embedding
Aleksandar Tomčić, Miloš Savić, Miloš Radovanović
Graph autoencoders (GAEs) are widely used for learning representations of dynamic graphs. However, their optimisation objectives typically do not take structural heterogeneity acro…
cs.SI2025
Dynamic Graph Embedding Through Hub-aware Random Walks
Aleksandar TomÄiÄ, MiloÅ¡ SaviÄ, DuÅ¡an SimiÄ +1
The role of high-degree nodes, or hubs, in shaping graph dynamics and structure is well-recognized in network science, yet their influence remains underexplored in the context of d…
cs.LG2024
Local Intrinsic Dimensionality for Dynamic Graph Embeddings
DuÅ¡ica KneževiÄ, MiloÅ¡ SaviÄ, MiloÅ¡ RadovanoviÄ
The notion of local intrinsic dimensionality (LID) has important theoretical implications and practical applications in the fields of data mining and machine learning. Recent resea…