Spatial-temporal Graph Convolutional Networks with Diversified Transformation for Dynamic Graph Representation Learning
This work addresses the challenge of dynamic graph representation learning for applications like communication networks, but it is incremental as it builds on existing GCN and sequence module approaches.
The paper tackled the problem of capturing complex temporal patterns in dynamic graphs by proposing STGCNDT, which integrates spatiotemporal information without separation, and it significantly outperformed state-of-the-art models in link weight estimation tasks on four communication network datasets.
Dynamic graphs (DG) are often used to describe evolving interactions between nodes in real-world applications. Temporal patterns are a natural feature of DGs and are also key to representation learning. However, existing dynamic GCN models are mostly composed of static GCNs and sequence modules, which results in the separation of spatiotemporal information and cannot effectively capture complex temporal patterns in DGs. To address this problem, this study proposes a spatial-temporal graph convolutional networks with diversified transformation (STGCNDT), which includes three aspects: a) constructing a unified graph tensor convolutional network (GTCN) using tensor M-products without the need to represent spatiotemporal information separately; b) introducing three transformation schemes in GTCN to model complex temporal patterns to aggregate temporal information; and c) constructing an ensemble of diversified transformation schemes to obtain higher representation capabilities. Empirical studies on four DGs that appear in communication networks show that the proposed STGCNDT significantly outperforms state-of-the-art models in solving link weight estimation tasks due to the diversified transformations.