Abstract
Sequence of graph snapshots have been commonly utilized in literature to represent changes in a dynamic graph. This approach may be suitable for small-size and slowly evolving graphs; however, it is associated with high storage overhead in massive and fast-evolving graphs because of replication of the entire graph from one snapshot to another at shorter temporal resolutions. This presents a drawback especially where efficient evolutionary analytics relies on the explanatory power of representing the dynamics of the graph across different temporal resolutions. In this paper, we propose a framework based on our Space–Time-varying graph (STVG) formalism which utilizes the Whole-graph approach to model the dynamics of a graph such that the evolution of the graph materializes in the time-varying changes of its Projected graphs. The STVG framework provides an approach to reduce high storage overhead in massively changing graph where new nodes and edges arrive every second. It affords the capability to extract Projected graphs at different time-windows and analyze their metrics across varying temporal resolutions. We demonstrate how the proposed STVG framework can be exploited to identify and extract evolutionary patterns in public bus transit graph using metrics such as graph density, volume and average path length. The results reveal evolutionary patterns in the overall network density, traffic congestion density as well as graph density with respect to bus movement at hourly, daily and monthly temporal resolutions.
Highlights
Evolutionary graph analytics have attracted attention from many research communities with the main purpose of understanding the changing pattern of real-world networks through evolutionary analysis of graph metrics and dynamic interactions between entities
Evolutionary graph analytics have been explored for use in different types of networks including web citation and co-authorship networks [1,2,3,4], online social networks [5,6,7,8,9,10], biology and disease networks [11,12,13,14], as well as in communication networks [15,16,17,18,19,20]
Experimental study we describe an experimental study and implementation, utilizing the Space–Time-varying graph (STVG) framework to carry out evolutionary graph analytics of a bus transit network
Summary
Evolutionary graph analytics have attracted attention from many research communities with the main purpose of understanding the changing pattern of real-world networks through evolutionary analysis of graph metrics and dynamic interactions between entities. In transit and mobility networks, nodes and edges are added to their graph on the temporal resolution of seconds, whereas in co-authorship networks, nodes and edges are added to their graph on the temporal resolution of months or years. These cases require different approaches for the evolutionary analysis
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
