Continuous-Time Dynamic Network Embeddings

@article{Nguyen2018ContinuousTimeDN,
  title={Continuous-Time Dynamic Network Embeddings},
  author={Giang Hoang Nguyen and John Boaz Lee and Ryan A. Rossi and Nesreen Ahmed and Eunyee Koh and Sungchul Kim},
  journal={Companion Proceedings of the The Web Conference 2018},
  year={2018}
}
Networks evolve continuously over time with the addition, deletion, and changing of links and nodes. [] Key Method The framework gives rise to methods for learning time-respecting embeddings from continuous-time dynamic networks. Overall, the experiments demonstrate the effectiveness of the proposed framework and dynamic network embedding approach as it achieves an average gain of 11.9% across all methods and graphs. The results indicate that modeling temporal dependencies in graphs is important for learning…

Figures and Tables from this paper

Dynamic Network Embeddings for Network Evolution Analysis

TLDR
This paper proposes a novel dynamic network embedding method that uses random walk to keep the proximity between nodes and applies dynamic Bernoulli embeddings to train discrete-time network embeddeddings in the same vector space without alignments to preserve the temporal continuity of stable nodes.

Dynamic Structural Role Node Embedding for User Modeling in Evolving Networks

TLDR
This article proposes a novel method, called HR2vec, that tracks historical topology information in dynamic networks to learn dynamic structural role embeddings and shows that this method outperforms other well-known methods in tasks where structural equivalence and historical information both play important roles.

TemporalNode2vec: Temporal Node Embedding in Temporal Networks

The goal of graph embedding is to learn a representation of graphs vertices in a latent low-dimensional space in order to encode the structural information that lies in graphs. While real-world

A Survey on Dynamic Network Embedding

TLDR
A novel taxonomy of existing dynamic network embedding techniques for the first time is proposed, including matrix factorization based, Skip-Gram based, autoencoder based, neural networks based and other embedding methods.

Learning Dynamic Context Graph Embedding

TLDR
This study proposes a dynamic graph embedding method to analyze the evolution patterns of dynamic graphs effectively and uses diffuse context sampling to preserve the proximity between nodes, and applies dynamic context graph embeddings to train discrete-time graph embedDings in the same vector space without alignments to preserved the temporal continuity of stable nodes.

Predictive Temporal Embedding of Dynamic Graphs

  • Aynaz TaheriT. Berger-Wolf
  • Computer Science
    2019 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining (ASONAM)
  • 2019
TLDR
This paper proposes an unsupervised encoder-decoder framework that projects a dynamic graph at each time step into a d-dimensional space, taking into account both the graph's topology and dynamics.

Entity Resolution in Dynamic Heterogeneous Networks

TLDR
This work describes two approaches for incorporating weighted temporal information into network embedding methods such as Graph Convolutional Networks (GCNs) and aggregates time-weighted edges and nodes, and demonstrates the effectiveness of the proposed TimeSage for link prediction tasks.

Motif-Preserving Temporal Network Embedding

TLDR
This work proposes MTNE, a novel embedding model for temporal networks that integrates the Hawkes process to stimulate the triad evolution process that preserves motif-aware high-order proximities, but also combines attention mechanism to distinguish the importance of different types of triads better.

On Structural vs. Proximity-based Temporal Node Embeddings

TLDR
In this work, a framework is introduced that incorporates different design options for extending static node embeddings to temporal settings: temporal combination schemes to introduce dynamics in otherwise static approaches, alignment methods that lead to comparability of embedding dimensions across time steps, and different edge operators for generating edgeembeddings from node embeddeddings.

Embedding Dynamic Attributed Networks by Modeling the Evolution Processes

TLDR
A high-order spatio-temporal embedding model is developed to track the evolutions of dynamic networks and it is shown that the proposed method outperforms all the baselines by a substantial margin for the tasks of dynamic link prediction and node classification.
...

References

SHOWING 1-10 OF 68 REFERENCES

Semi-supervised Graph Embedding Approach to Dynamic Link Prediction

TLDR
A simple discrete-time semi-supervised graph embedding approach to link prediction in dynamic networks that is comparable to state of the art methods in link formation prediction and outperforms state-of-the-art baseline Methods in link dissolution prediction.

Time-Evolving Relational Classification and Ensemble Methods

TLDR
A novel framework for discovering temporal-relational representations for classification is proposed that considers transformations over all the evolving relational components (attributes, edges, and nodes) in order to accurately incorporate temporal dependencies into relational models.

Dynamic mixed membership blockmodel for evolving networks

TLDR
A state space mixed membership stochastic blockmodel which can track across time the evolving roles of the actors and derive an efficient variational inference procedure for this model, and applies it to the Enron email networks, and rewiring gene regulatory networks of yeast.

node2vec: Scalable Feature Learning for Networks

TLDR
In node2vec, an algorithmic framework for learning continuous feature representations for nodes in networks, a flexible notion of a node's network neighborhood is defined and a biased random walk procedure is designed, which efficiently explores diverse neighborhoods.

GraRep: Learning Graph Representations with Global Structural Information

TLDR
A novel model for learning vertex representations of weighted graphs that integrates global structural information of the graph into the learning process and significantly outperforms other state-of-the-art methods in such tasks.

metapath2vec: Scalable Representation Learning for Heterogeneous Networks

TLDR
Two scalable representation learning models, namely metapath2vec and metapATH2vec++, are developed that are able to not only outperform state-of-the-art embedding models in various heterogeneous network mining tasks, but also discern the structural and semantic correlations between diverse network objects.

LINE: Large-scale Information Network Embedding

TLDR
A novel network embedding method called the ``LINE,'' which is suitable for arbitrary types of information networks: undirected, directed, and/or weighted, and optimizes a carefully designed objective function that preserves both the local and global network structures.

Modeling the evolution of discussion topics and communication to improve relational classification

TLDR
The TENC paired with the latent topics significantly improves performance over the baseline classifiers that only take into account the static properties of the topics and communications, and shows that the TENC can be used to accurately model the complete-set of temporal dynamics in time-evolving communication networks.

GraphScope: parameter-free mining of large time-evolving graphs

TLDR
The efficiency and effectiveness of the GraphScope is demonstrated, which is designed to operate on large graphs, in a streaming fashion, on real datasets from several diverse domains, and produces meaningful time-evolving patterns that agree with human intuition.

Temporal Networks

...