Embedding Networks with Edge Attributes

By Palash Goyal, Homa Hosseinmardi, Emilio Ferrara, Aram Galstyan. 2018

13 citations recorded by the source corpus.

Predicting links in information networks requires deep understanding and careful modeling of network structure. Network embedding, which aims to learn low-dimensional representations of nodes, has been used successfully for the task of link prediction in the past few decades. Existing methods utilize the observed edges in the network to model the interactions between nodes and learn representations which explain the behavior. In addition to the presence of edges, networks often have information which can be used to improve the embedding. For example, in author collaboration networks, the bag of words representing the abstract of co-authored paper can be used as edge attributes. In this paper, we propose a novel approach, which uses the edges and their associated labels to learn node embeddings. Our model jointly optimizes higher order node neighborhood, social roles and edge attributes reconstruction error using deep architecture which can model highly non-linear interactions. We demonstrate the efficacy of our model over existing state-of-the-art methods on two real world data sets. We observe that such attributes can improve the quality of embedding and yield better performance in link prediction.

Subfields: Artificial Intelligence, Molecular Biology, Statistical and Nonlinear Physics

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Arquimedes Canedo
2. Sujit Rokka Chhetri
3. Palash Goyal
4. Mark Heimann
5. David M. Beskow

In Molecular Biology

1. Palash Goyal

In Statistical and Nonlinear Physics

1. Arquimedes Canedo
2. Sujit Rokka Chhetri
3. Palash Goyal
4. David M. Beskow
5. Mark Heimann

Citations in the corpus

• Debiasing Community Detection: The Importance of Lowly Connected Nodes (2019, neutral): “In addition to CESNA, other methods have been proposed, such as Block-LDA [2], PAICAN [4], shared latent space models such as CLSM [5], and embedding based approaches like LANE [12], which utilize node attributes in order to detect communities, or ELAINE [11] which utilizes edge attributes.”
• dyngraph2vec: Capturing Network Dynamics using Dynamic Graph Representation Learning (2018, background): “These models learn latent representations of the static graph and use them to predict missing links [10, 11, 12, 13, 8, 9, 14].”