DeepAI AI Chat
Log In Sign Up

Decoupled Graph Neural Networks for Large Dynamic Graphs

by   Yanping Zheng, et al.
Renmin University of China

Real-world graphs, such as social networks, financial transactions, and recommendation systems, often demonstrate dynamic behavior. This phenomenon, known as graph stream, involves the dynamic changes of nodes and the emergence and disappearance of edges. To effectively capture both the structural and temporal aspects of these dynamic graphs, dynamic graph neural networks have been developed. However, existing methods are usually tailored to process either continuous-time or discrete-time dynamic graphs, and cannot be generalized from one to the other. In this paper, we propose a decoupled graph neural network for large dynamic graphs, including a unified dynamic propagation that supports efficient computation for both continuous and discrete dynamic graphs. Since graph structure-related computations are only performed during the propagation process, the prediction process for the downstream task can be trained separately without expensive graph computations, and therefore any sequence model can be plugged-in and used. As a result, our algorithm achieves exceptional scalability and expressiveness. We evaluate our algorithm on seven real-world datasets of both continuous-time and discrete-time dynamic graphs. The experimental results demonstrate that our algorithm achieves state-of-the-art performance in both kinds of dynamic graphs. Most notably, the scalability of our algorithm is well illustrated by its successful application to large graphs with up to over a billion temporal edges and over a hundred million nodes.


page 1

page 2

page 3

page 4


Efficient-Dyn: Dynamic Graph Representation Learning via Event-based Temporal Sparse Attention Network

Static graph neural networks have been widely used in modeling and repre...

FDGNN: Fully Dynamic Graph Neural Network

Dynamic Graph Neural Networks recently became more and more important as...

Continuous Graph Neural Networks

This paper builds the connection between graph neural networks and tradi...

Instant Graph Neural Networks for Dynamic Graphs

Graph Neural Networks (GNNs) have been widely used for modeling graph-st...

Online force-directed algorithms for visualization of dynamic graphs

Force-directed (FD) algorithms can be used to explore relationships in s...

TCL: Transformer-based Dynamic Graph Modelling via Contrastive Learning

Dynamic graph modeling has recently attracted much attention due to its ...

EvoNet: A Neural Network for Predicting the Evolution of Dynamic Graphs

Neural networks for structured data like graphs have been studied extens...