Graph-Free Learning in Graph-Structured Data: A More Efficient and Accurate Spatiotemporal Learning Perspective
This work addresses inefficiencies in spatiotemporal graph learning for researchers and practitioners, offering a more efficient and accurate method, though it is incremental as it builds on existing models.
The paper tackles the problem of spatiotemporal learning by showing that carefully designed adjacency matrices in graph convolutional networks are largely ineffective, and proposes a Graph-Free Spatial (GFS) module that replaces graph convolutions, achieving significant improvements in efficiency and accuracy, especially for large-scale graph data.
Spatiotemporal learning, which aims at extracting spatiotemporal correlations from the collected spatiotemporal data, is a research hotspot in recent years. And considering the inherent graph structure of spatiotemporal data, recent works focus on capturing spatial dependencies by utilizing Graph Convolutional Networks (GCNs) to aggregate vertex features with the guidance of adjacency matrices. In this paper, with extensive and deep-going experiments, we comprehensively analyze existing spatiotemporal graph learning models and reveal that extracting adjacency matrices with carefully design strategies, which are viewed as the key of enhancing performance on graph learning, are largely ineffective. Meanwhile, based on these experiments, we also discover that the aggregation itself is more important than the way that how vertices are aggregated. With these preliminary, a novel efficient Graph-Free Spatial (GFS) learning module based on layer normalization for capturing spatial correlations in spatiotemporal graph learning. The proposed GFS module can be easily plugged into existing models for replacing all graph convolution components. Rigorous theoretical proof demonstrates that the time complexity of GFS is significantly better than that of graph convolution operation. Extensive experiments verify the superiority of GFS in both the perspectives of efficiency and learning effect in processing graph-structured data especially extreme large scale graph data.