Temporal Network Embedding via Tensor Factorization
This work addresses the challenge of modeling evolving networks for applications like link prediction, representing an incremental improvement over prior temporal network embedding methods.
The paper tackles the problem of learning embeddings for temporal networks, where edges change over time, by proposing Toffee, a tensor factorization-based method that captures temporal interdependence and periodic changes, resulting in outperforming existing methods on link prediction tasks across multiple real-world datasets.
Representation learning on static graph-structured data has shown a significant impact on many real-world applications. However, less attention has been paid to the evolving nature of temporal networks, in which the edges are often changing over time. The embeddings of such temporal networks should encode both graph-structured information and the temporally evolving pattern. Existing approaches in learning temporally evolving network representations fail to capture the temporal interdependence. In this paper, we propose Toffee, a novel approach for temporal network representation learning based on tensor decomposition. Our method exploits the tensor-tensor product operator to encode the cross-time information, so that the periodic changes in the evolving networks can be captured. Experimental results demonstrate that Toffee outperforms existing methods on multiple real-world temporal networks in generating effective embeddings for the link prediction tasks.