DynG2G: An Efficient Stochastic Graph Embedding Method for Temporal Graphs. (arXiv:2109.13441v2 [cs.LG] UPDATED)

Dynamic graph embedding has gained great attention recently due to its
capability of learning low dimensional graph representations for complex
temporal graphs with high accuracy. However, recent advances mostly focus on
learning node embeddings as deterministic "vectors" for static graphs yet
disregarding the key graph temporal dynamics and the evolving uncertainties
associated with node embedding in the latent space. In this work, we propose an
efficient stochastic dynamic graph embedding method (DynG2G) that applies an
inductive feed-forward encoder trained with …

arxiv embedding graph graphs stochastic temporal