4 papers
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…
Dynamic Graph Embedding Through Hub-aware Random Walks
Aleksandar Tomčić, Miloš Savić, Dušan Simić +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…
Local Intrinsic Dimensionality for Dynamic Graph Embeddings
Dušica Knežević, Miloš Savić, Miloš Radovanović
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…
Local Intrinsic Dimensionality Measures for Graphs, with Applications to Graph Embeddings
Miloš Savić, Vladimir Kurbalija, Miloš Radovanović
The notion of local intrinsic dimensionality (LID) is an important advancement in data dimensionality analysis, with applications in data mining, machine learning and similarity se…