Direct Embedding of Temporal Network Edges via Time-Decayed Line Graphs
This work addresses limitations in temporal network analysis for researchers and practitioners, offering a more direct and theoretically grounded approach, though it is incremental as it builds on existing line graph methods.
The authors tackled the problem of machine learning on temporal networks by proposing a method that directly embeds edges using time-decayed line graphs, avoiding discretization of continuous time and indirect edge representation. Empirical results on real-world networks showed efficacy and efficiency in edge classification and temporal link prediction tasks.
Temporal networks model a variety of important phenomena involving timed interactions between entities. Existing methods for machine learning on temporal networks generally exhibit at least one of two limitations. First, time is assumed to be discretized, so if the time data is continuous, the user must determine the discretization and discard precise time information. Second, edge representations can only be calculated indirectly from the nodes, which may be suboptimal for tasks like edge classification. We present a simple method that avoids both shortcomings: construct the line graph of the network, which includes a node for each interaction, and weigh the edges of this graph based on the difference in time between interactions. From this derived graph, edge representations for the original network can be computed with efficient classical methods. The simplicity of this approach facilitates explicit theoretical analysis: we can constructively show the effectiveness of our method's representations for a natural synthetic model of temporal networks. Empirical results on real-world networks demonstrate our method's efficacy and efficiency on both edge classification and temporal link prediction.