Heterogeneous Information Network Embedding for Meta Path based Proximity
arXiv:1701.05291
Abstract
A network embedding is a representation of a large graph in a low-dimensional space, where vertices are modeled as vectors. The objective of a good embedding is to preserve the proximity between vertices in the original graph. This way, typical search and mining methods can be applied in the embedded space with the help of off-the-shelf multidimensional indexing approaches. Existing network embedding techniques focus on homogeneous networks, where all vertices are considered to belong to a single class.
Cited by in corpus (10)
- A Survey on Network Embedding
- HAHE: Hierarchical Attentive Heterogeneous Information Network Embedding
- Deep Representation Learning for Social Network Analysis
- Tree Structure-Aware Graph Representation Learning via Integrated Hierarchical Aggregation and Relational Metric Learning
- Representation Learning for Heterogeneous Information Networks via Embedding Events
- Triple2Vec: Learning Triple Embeddings from Knowledge Graphs
- A Framework for Joint Unsupervised Learning of Cluster-Aware Embedding for Heterogeneous Networks
- Path-Based Reasoning over Heterogeneous Networks for Recommendation via Bidirectional Modeling
- Meta-Graph Based HIN Spectral Embedding: Methods, Analyses, and Insights
- Similarity Modeling on Heterogeneous Networks via Automatic Path Discovery