WalkingTime: Dynamic Graph Embedding Using Temporal-Topological Flows
This work addresses the challenge of embedding dynamic graphs for applications like network analysis and datamining, offering a new approach that is incremental in its methodological innovation.
The paper tackles the problem of dynamic network embedding by proposing WalkingTime, a novel algorithm that uses temporal-topological flows to handle continuously occurring phenomena without time discretization, achieving improved performance on real-attributed knowledge graphs and streaming graphs.
Increased attention has been paid over the last four years to dynamic network embedding. Existing dynamic embedding methods, however, consider the problem as limited to the evolution of a topology over a sequence of global, discrete states. We propose a novel embedding algorithm, WalkingTime, based on a fundamentally different handling of time, allowing for the local consideration of continuously occurring phenomena; while others consider global time-steps to be first-order citizens of the dynamic environment, we hold flows comprised of temporally and topologically local interactions as our primitives, without any discretization or alignment of time-related attributes being necessary. Keywords: dynamic networks , representation learning , dynamic graph embedding , time-respecting paths , temporal-topological flows , temporal random walks , temporal networks , real-attributed knowledge graphs , streaming graphs , online networks , asynchronous graphs , asynchronous networks , graph algorithms , deep learning , network analysis , datamining , network science