Graph Gaussian Embedding Algorithm
Jump to navigation
Jump to search
A Graph Gaussian Embedding Algorithm is a Graph Embedding Algorithm that is based on a Gaussian distribution.
- Example(s):
- Counter-Example(s):
- See: Gaussian Process, Gaussian Vector Space.
References
2017
- (Bojchevski & Gunnemann, 2017) ⇒ Aleksandar Bojchevski, and Stephan Gunnemann (2017). "Deep Gaussian Embedding of Graphs: Unsupervised Inductive Learning via Ranking". In: Preprint arXiv:1707.03815.
- QUOTE: All existing (attributed) graph embedding approaches represent each node by a single point in a low-dimensional continuous vector space. Representing the nodes simply as points, however, has a crucial limitation: we do not have information about the uncertainty of that representation. Yet uncertainty is inherent when describing a node in a complex graph by a single point only. Imagine a node for which the different sources of information are conflicting with each other, e.g. pointing to different communities or even revealing contradicting underlying patterns. Such discrepancy should be reflected in the uncertainty of its embedding. As a solution to this problem, we introduce a novel embedding approach that represents nodes as Gaussian distributions: each node becomes a full distribution rather than a single point. Thereby, we capture uncertainty about its representation.