Adaptive Spatiotemporal Augmentation for Improving Dynamic Graph Learning
This work addresses noise issues in dynamic graph neural networks for applications like social network analysis, though it is incremental as it builds on existing augmentation techniques.
The paper tackles the problem of noise in dynamic graph learning by proposing STAA, a spatiotemporal activity-aware augmentation method that identifies and reduces noisy edges, resulting in improved performance over other methods in node classification and link prediction tasks.
Dynamic graph augmentation is used to improve the performance of dynamic GNNs. Most methods assume temporal locality, meaning that recent edges are more influential than earlier edges. However, for temporal changes in edges caused by random noise, overemphasizing recent edges while neglecting earlier ones may lead to the model capturing noise. To address this issue, we propose STAA (SpatioTemporal Activity-Aware Random Walk Diffusion). STAA identifies nodes likely to have noisy edges in spatiotemporal dimensions. Spatially, it analyzes critical topological positions through graph wavelet coefficients. Temporally, it analyzes edge evolution through graph wavelet coefficient change rates. Then, random walks are used to reduce the weights of noisy edges, deriving a diffusion matrix containing spatiotemporal information as an augmented adjacency matrix for dynamic GNN learning. Experiments on multiple datasets show that STAA outperforms other dynamic graph augmentation methods in node classification and link prediction tasks.