Learning Dynamic Graphs via Tensorized and Lightweight Graph Convolutional Networks
This work addresses the challenge of modeling intricate spatio-temporal dependencies in dynamic graphs for applications in real-world scenarios, representing an incremental improvement over existing methods.
The paper tackles the problem of disrupted spatio-temporal dependencies in dynamic graph learning by proposing a Tensorized Lightweight Graph Convolutional Network (TLGCN), which achieves state-of-the-art performance in weight estimation tasks on four real-world datasets.
A dynamic graph (DG) is frequently encountered in numerous real-world scenarios. Consequently, A dynamic graph convolutional network (DGCN) has been successfully applied to perform precise representation learning on a DG. However, conventional DGCNs typically consist of a static GCN coupled with a sequence neural network (SNN) to model spatial and temporal patterns separately. This decoupled modeling mechanism inherently disrupts the intricate spatio-temporal dependencies. To address the issue, this study proposes a novel Tensorized Lightweight Graph Convolutional Network (TLGCN) for accurate dynamic graph learning. It mainly contains the following two key concepts: a) designing a novel spatio-temporal information propagation method for joint propagation of spatio-temporal information based on the tensor M-product framework; b) proposing a tensorized lightweight graph convolutional network based on the above method, which significantly reduces the memory occupation of the model by omitting complex feature transformation and nonlinear activation. Numerical experiments on four real-world datasets demonstrate that the proposed TLGCN outperforms the state-of-the-art models in the weight estimation task on DGs.