Temporal Aggregation and Propagation Graph Neural Networks for Dynamic Representation

Tongya Zheng

doi:10.1109/TKDE.2023.3265271

Temporal Aggregation and Propagation Graph Neural Networks for Dynamic Representation

2023-10-01

5

OA

AI

DOI：10.1109/TKDE.2023.3265271

Original

Original request for help

Save

Abstract

En 中文

Temporal graphs exhibit dynamic interactions between nodes over continuous time, whose topologies evolve with time elapsing. The whole temporal neighborhood of nodes reveals the varying preferences of nodes. However, previous works usually generate dynamic representation with limited neighbors for simplicity, which results in both inferior performance and high latency of online inference. Therefore, in this paper, we propose a novel method of temporal graph convolution with the whole neighborhood, namely Temporal Aggregation and Propagation Graph Neural Networks (TAP-GNN). Specifically, we first analyze the computational complexity of the dynamic representation problem by unfolding the temporal graph in a message-passing paradigm. The expensive complexity motivates us to design the AP (aggregation and propagation) block, which significantly reduces the repeated computation of historical neighbors. The final TAP-GNN supports online inference in the graph stream scenario, which incorporates the temporal information into node embeddings with a temporal activation function and a projection layer besides several AP blocks. Experimental results on various real-life temporal networks show that our proposed TAP-GNN outperforms existing temporal graph methods by a large margin in terms of both predictive performance and online inference latency.

Keywords:

Computational modeling

Predictive models

Graph neural networks

Convolution

Task analysis

Computational complexity

Topology

Dynamic graph

Graph embedding

graph neural networks

link prediction

temporal graph

Temporal Aggregation and Propagation Graph Neural Networks for Dynamic Representation

Abstract

Journal

Organization