Streaming Graph Neural Networks

TL;DR

This paper introduces DGNN, a novel dynamic graph neural network that effectively models evolving graph structures by capturing sequential interactions, time intervals, and information propagation, improving analysis of real-world dynamic networks.

Contribution

The paper presents DGNN, a new framework for dynamic graphs that incorporates sequential edge information, timing, and propagation to enhance graph neural network capabilities.

Findings

DGNN outperforms static GNNs on dynamic graph tasks.

Incorporating temporal information improves predictive accuracy.

Experimental results validate the effectiveness of DGNN.

Abstract

Graphs are essential representations of many real-world data such as social networks. Recent years have witnessed the increasing efforts made to extend the neural network models to graph-structured data. These methods, which are usually known as the graph neural networks, have been applied to advance many graphs related tasks such as reasoning dynamics of the physical system, graph classification, and node classification. Most of the existing graph neural network models have been designed for static graphs, while many real-world graphs are inherently dynamic. For example, social networks are naturally evolving as new users joining and new relations being created. Current graph neural network models cannot utilize the dynamic information in dynamic graphs. However, the dynamic information has been proven to enhance the performance of many graph analytic tasks such as community detection and link prediction. Hence, it is necessary to design dedicated graph neural networks for dynamic graphs. In this paper, we propose DGNN, a new {\bf D}ynamic {\bf G}raph {\bf N}eural {\bf N}etwork model, which can model the dynamic information as the graph evolving. In particular, the proposed framework can keep updating node information by capturing the sequential information of edges (interactions), the time intervals between edges and information propagation coherently. Experimental results on various dynamic graphs demonstrate the effectiveness of the proposed framework.