TME-BNA: Temporal Motif-Preserving Network Embedding with Bicomponent Neighbor Aggregation
This addresses the challenge of embedding dynamic networks for tasks like link prediction, but it appears incremental as it builds on existing GNN approaches with motif-based features.
The paper tackles the problem of temporal network embedding by proposing TME-BNA, a method that uses temporal motifs and bicomponent neighbor aggregation to capture network evolution, achieving effectiveness in experiments on three public datasets.
Evolving temporal networks serve as the abstractions of many real-life dynamic systems, e.g., social network and e-commerce. The purpose of temporal network embedding is to map each node to a time-evolving low-dimension vector for downstream tasks, e.g., link prediction and node classification. The difficulty of temporal network embedding lies in how to utilize the topology and time information jointly to capture the evolution of a temporal network. In response to this challenge, we propose a temporal motif-preserving network embedding method with bicomponent neighbor aggregation, named TME-BNA. Considering that temporal motifs are essential to the understanding of topology laws and functional properties of a temporal network, TME-BNA constructs additional edge features based on temporal motifs to explicitly utilize complex topology with time information. In order to capture the topology dynamics of nodes, TME-BNA utilizes Graph Neural Networks (GNNs) to aggregate the historical and current neighbors respectively according to the timestamps of connected edges. Experiments are conducted on three public temporal network datasets, and the results show the effectiveness of TME-BNA.