2018/05/19 by Bo Kang, Jefrey Lijffijt, Kang, Bo +3 · 2 citations
Computer Science · Mathematics · Physics and Astronomy · #Advanced Graph Neural Networks #Complex Network Analysis Techniques #Cooperative Communication and Network Coding #FOS: Computer and information sciences #Information Theory (cs.IT) #Machine Learning (cs.LG) #Machine Learning (stat.ML) #cs.IT #cs.LG #math.IT #stat.ML
paper · pdf · doi:10.48550/arxiv.1805.07544
openalex publication_date 2018/05/19 · arxiv created 2018/10/16 · arxiv updated 2018/10/17 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
Network Embeddings (NEs) map the nodes of a given network into d-dimensional Euclidean space ℝd. Ideally, this mapping is such that `similar' nodes are mapped onto nearby points, such that the NE can be used for purposes such as link prediction (if `similar' means being `more likely to be connected') or classification (if `similar' means `being more likely to have the same label'). In recent years various methods for NE have been introduced, all following a similar strategy: defining a notion of similarity between nodes (typically some distance measure within the network), a distance measure in the embedding space, and a loss function that penalizes large distances for similar nodes and small distances for dissimilar nodes. A difficulty faced by existing methods is that certain networks are fundamentally hard to embed due to their structural properties: (approximate) multipartiteness, certain degree distributions, assortativity, etc. To overcome this, we introduce a conceptual innovation to the NE literature and propose to create Conditional Network Embeddings (CNEs); embeddings that maximally add information with respect to given structural properties (e.g. node degrees, block densities, etc.). We use a simple Bayesian approach to achieve this, and propose a block stochastic gradient descent algorithm for fitting it efficiently. We demonstrate that CNEs are superior for link prediction and multi-label classification when compared to state-of-the-art methods, and this without adding significant mathematical or computational complexity. Finally, we illustrate the potential of CNE for network visualization.