Dynamic Node Embeddings from Edge Streams
arXiv:1904.06449
Abstract
Networks evolve continuously over time with the addition, deletion, and changing of links and nodes. Such temporal networks (or edge streams) consist of a sequence of timestamped edges and are seemingly ubiquitous. Despite the importance of accurately modeling the temporal information, most embedding methods ignore it entirely or approximate the temporal network using a sequence of static snapshot graphs. In this work, we propose using the notion of temporal walks for learning dynamic embeddings from temporal networks. Temporal walks capture the temporally valid interactions (e.g., flow of information, spread of disease) in the dynamic network in a lossless fashion. Based on the notion of temporal walks, we describe a general class of embeddings called continuous-time dynamic network embeddings (CTDNEs) that completely avoid the issues and problems that arise when approximating the temporal network as a sequence of static snapshot graphs. Unlike previous work, CTDNEs learn dynamic node embeddings directly from the temporal network at the finest temporal granularity and thus use only temporally valid information. As such CTDNEs naturally support online learning of the node embeddings in a streaming real-time fashion. Finally, the experiments demonstrate the effectiveness of this class of embedding methods that leverage temporal walks as it achieves an average gain in AUC of 11.9% across all methods and graphs.
arXiv commentIEEE Transactions on Emerging Topics in Computational Intelligence (TETIC)
References in corpus (22)
- Efficient Estimation of Word Representations in Vector Space
- The structure of scientific collaboration networks
- struc2vec: Learning Node Representations from Structural Identity
- Link Prediction Based on Local Random Walk
- Attributed Social Network Embedding
- Attributed Network Embedding for Learning in a Dynamic Environment
- Graph Metrics for Temporal Networks
- Scalable Link Prediction in Dynamic Networks via Non-Negative Matrix Factorization
- Role Discovery in Networks
- Node Embedding over Temporal Graphs
- Deep Generative Dual Memory Network for Continual Learning
- Learning Role-based Graph Embeddings
- DyLink2Vec: Effective Feature Representation for Link Prediction in Dynamic Networks
- Efficient Representation Learning Using Random Walks for Dynamic Graphs
- Inductive Representation Learning in Large Attributed Graphs
- PSDVec: a Toolbox for Incremental and Scalable Word Embedding
- A Framework for Generalizing Graph-based Representation Learning Methods
- Incremental Method for Spectral Clustering of Increasing Orders
- Incremental Skip-gram Model with Negative Sampling
- Models for Capturing Temporal Smoothness in Evolving Networks for Learning Latent Representation of Nodes
- Heterogeneous Network Motifs
- Semi-supervised Graph Embedding Approach to Dynamic Link Prediction