Time-Aware Dynamic Graph Embedding for Asynchronous Structural Evolution

Dynamic graphs refer to graphs whose structure dynamically changes over time. Despite the benefits of learning vertex representations (i.e., embeddings) for dynamic graphs, existing works merely view a dynamic graph as a sequence of changes within the vertex connections, neglecting the crucial asynchronous nature of such dynamics where the evolution of each local structure starts at different times and lasts for various durations. To maintain asynchronous structural evolutions within the graph, we innovatively formulate dynamic graphs as temporal edge sequences associated with joining time of vertices (ToV) and timespan of edges (ToE). Then, a time-aware Transformer is proposed to embed vertices' dynamic connections and ToEs into the learned vertex representations. Meanwhile, we treat each edge sequence as a whole and embed its ToV of the first vertex to further encode the time-sensitive information. Extensive evaluations on several datasets show that our approach outperforms the state-of-the-art in a wide range of graph mining tasks. At the same time, it is very efficient and scalable for embedding large-scale dynamic graphs.

Automated summary

Dynamic graphs are graphs whose structure changes over time. Existing approaches only consider dynamic graphs as a sequence of changes in vertex connections, ignoring the asynchronous nature of the dynamics where the evolution of each local structure starts at different times and lasts for various durations. To address this, we propose a novel representation of dynamic graphs as temporal edge sequences associated with joining time of vertices (ToV) and timespan of edges (ToE). We also introduce a time-aware Transformer to embed the dynamic connections and ToEs into learned vertex representations, along with encoding time-sensitive information. Our approach outperforms the state-of-the-art in various graph mining tasks and is efficient for embedding large-scale dynamic graphs.