EmbeddingVis: A Visual Analytics Approach to Comparative Network Embedding Inspection
arXiv:1808.09074
Abstract
Constructing latent vector representation for nodes in a network through embedding models has shown its practicality in many graph analysis applications, such as node classification, clustering, and link prediction. However, despite the high efficiency and accuracy of learning an embedding model, people have little clue of what information about the original network is preserved in the embedding vectors. The abstractness of low-dimensional vector representation, stochastic nature of the construction process, and non-transparent hyper-parameters all obscure understanding of network embedding results. Visualization techniques have been introduced to facilitate embedding vector inspection, usually by projecting the embedding space to a two-dimensional display. Although the existing visualization methods allow simple examination of the structure of embedding space, they cannot support in-depth exploration of the embedding vectors. In this paper, we design an exploratory visual analytics system that supports the comparative visual interpretation of embedding vectors at the cluster, instance, and structural levels. To be more specific, it facilitates comparison of what and how node metrics are preserved across different embedding models and investigation of relationships between node metrics and selected embedding vectors. Several case studies confirm the efficacy of our system. Experts' feedback suggests that our approach indeed helps them better embrace the understanding of network embedding models.
arXiv commentProceedings of IEEE VIS 2018 (VAST 2018) (to appear), Berlin, Germany, Oct 21-26, 2018
References in corpus (10)
- Efficient Estimation of Word Representations in Vector Space
- Statistical mechanics of complex networks
- Benchmark graphs for testing community detection algorithms
- struc2vec: Learning Node Representations from Structural Identity
- Attributed Social Network Embedding
- Attributed Network Embedding for Learning in a Dynamic Environment
- A Theoretical Analysis of NDCG Type Ranking Measures
- Embedding Projector: Interactive Visualization and Interpretation of Embeddings
- SSP: Semantic Space Projection for Knowledge Graph Embedding with Text Descriptions
- PixelSNE: Visualizing Fast with Just Enough Precision via Pixel-Aligned Stochastic Neighbor Embedding