Temporal Network Representation Learning

04/12/2019
by   John Boaz Lee, et al.
22

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 introduce the notion of temporal walks for learning dynamic embeddings from temporal networks. Temporal walks capture the temporally valid interactions (, 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. The experiments demonstrate the effectiveness of this class of embedding methods for prediction in temporal networks.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
11/22/2021

WalkingTime: Dynamic Graph Embedding Using Temporal-Topological Flows

Increased attention has been paid over the last four years to dynamic ne...
research
10/26/2021

Quantitative Evaluation of Snapshot Graphs for the Analysis of Temporal Networks

One of the most common approaches to the analysis of dynamic networks is...
research
09/21/2020

From Static to Dynamic Node Embeddings

We introduce a general framework for leveraging graph stream data for te...
research
11/22/2011

Representations and Ensemble Methods for Dynamic Relational Classification

Temporal networks are ubiquitous and evolve over time by the addition, d...
research
01/15/2021

Inductive Representation Learning in Temporal Networks via Causal Anonymous Walks

Temporal networks serve as abstractions of many real-world dynamic syste...
research
09/24/2020

EPNE: Evolutionary Pattern Preserving Network Embedding

Information networks are ubiquitous and are ideal for modeling relationa...
research
10/18/2019

Temporal Network Sampling

Temporal networks representing a stream of timestamped edges are seeming...

Please sign up or login with your details

Forgot password? Click here to reset