Graph-Free Learning in Graph-Structured Data: A More Efficient and Accurate Spatiotemporal Learning Perspective

by   Xu Wang, et al.

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.


page 1

page 2

page 3

page 4


Spatial Aggregation and Temporal Convolution Networks for Real-time Kriging

Spatiotemporal kriging is an important application in spatiotemporal dat...

Dynamic Causal Graph Convolutional Network for Traffic Prediction

Modeling complex spatiotemporal dependencies in correlated traffic serie...

Graph-Time Convolutional Neural Networks: Architecture and Theoretical Analysis

Devising and analyzing learning models for spatiotemporal network data i...

Dynamic Spatiotemporal Graph Convolutional Neural Networks for Traffic Data Imputation with Complex Missing Patterns

Missing data is an inevitable and ubiquitous problem for traffic data co...

Spatiotemporal Propagation Learning for Network-Wide Flight Delay Prediction

Demystifying the delay propagation mechanisms among multiple airports is...

Graph-Time Convolutional Neural Networks

Spatiotemporal data can be represented as a process over a graph, which ...

Disentangled Spatiotemporal Graph Generative Models

Spatiotemporal graph represents a crucial data structure where the nodes...

Please sign up or login with your details

Forgot password? Click here to reset