From Node Embedding To Community Embedding
By Vincent Wenchen Zheng, Sandro Cavallari, Hongyun Cai, Kevin Chen-Chuan Chang, Erik Cambria. 2016
34 citations recorded by the source corpus.
Most of the existing graph embedding methods focus on nodes, which aim to output a vector representation for each node in the graph such that two nodes being "close" on the graph are close too in the low-dimensional space. Despite the success of embedding individual nodes for graph analytics, we notice that an important concept of embedding communities (i.e., groups of nodes) is missing. Embedding communities is useful, not only for supporting various community-level applications, but also to help preserve community structure in graph embedding. In fact, we see community embedding as providing a higher-order proximity to define the node closeness, whereas most of the popular graph embedding methods focus on first-order and/or second-order proximities. To learn the community embedding, we hinge upon the insight that community embedding and node embedding reinforce with each other. As a result, we propose ComEmbed, the first community embedding method, which jointly optimizes the community embedding and node embedding together. We evaluate ComEmbed on real-world data sets. We show it outperforms the state-of-the-art baselines in both tasks of node classification and community prediction.
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
Citations in the corpus
- A Comprehensive Survey of Graph Embedding: Problems, Techniques, and Applications (2017, background): “ embedding. It jointly optimizes the community detection and community-aware node embedding in a unified framework. A node’s embedding is similar to the embedding of the community which it belongs to. [90] also jointly solves node embedding, community detection and community embedding together. Rathe”
- Semantic Proximity Search on Heterogeneous Graph by Proximity Embedding (2017, background): “2015) and community embedding (Zheng et al. 2016), but they do not directly encode the network structure between two nodes.”
- Topological Recurrent Neural Network for Diffusion Prediction (2017, background): “ComE [34], [35] further considers community-aware high-order proximity for node embedding and community embedding.”
- Distance-Aware DAG Embedding for Proximity Search on Heterogeneous Graphs (2018, unknown): “2015), node2vec (Grover and Leskovec 2016), and more (Zheng et al. 2016; Nie, Zhu, and Li 2017; Nikolentzos, Meladianos, and Vazirgiannis 2017).”