SPAN: Subgraph Prediction Attention Network for Dynamic Graphs
This addresses the problem of predicting subgraph evolution for researchers and practitioners in graph analysis, representing an incremental improvement over existing methods.
The paper tackles subgraph prediction in dynamic graphs by proposing an end-to-end model that maps current subgraph structures to future ones, outperforming state-of-the-art methods with gains of 5.02% to 10.88% in experiments on real-world graphs.
This paper proposes a novel model for predicting subgraphs in dynamic graphs, an extension of traditional link prediction. This proposed end-to-end model learns a mapping from the subgraph structures in the current snapshot to the subgraph structures in the next snapshot directly, i.e., edge existence among multiple nodes in the subgraph. A new mechanism named cross-attention with a twin-tower module is designed to integrate node attribute information and topology information collaboratively for learning subgraph evolution. We compare our model with several state-of-the-art methods for subgraph prediction and subgraph pattern prediction in multiple real-world homogeneous and heterogeneous dynamic graphs, respectively. Experimental results demonstrate that our model outperforms other models in these two tasks, with a gain increase from 5.02% to 10.88%.