Temporal Aggregation and Propagation Graph Neural Networks for Dynamic Representation

by   Tongya Zheng, et al.
National University of Singapore
Zhejiang University

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 firstly 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. Our code is available at <https://github.com/doujiang-zheng/TAP-GNN>.


page 11

page 15


Transition Propagation Graph Neural Networks for Temporal Networks

Researchers of temporal networks (e.g., social networks and transaction ...

Learning to Evolve on Dynamic Graphs

Representation learning in dynamic graphs is a challenging problem becau...

Redundancy-Free Computation Graphs for Graph Neural Networks

Graph Neural Networks (GNNs) are based on repeated aggregations of infor...

InkStream: Real-time GNN Inference on Streaming Graphs via Incremental Update

Classic Graph Neural Network (GNN) inference approaches, designed for st...

BRIGHT – Graph Neural Networks in Real-Time Fraud Detection

Detecting fraudulent transactions is an essential component to control r...

APAN: Asynchronous Propagation Attention Network for Real-time Temporal Graph Embedding

Limited by the time complexity of querying k-hop neighbors in a graph da...

Learning Dynamic Preference Structure Embedding From Temporal Networks

The dynamics of temporal networks lie in the continuous interactions bet...

Code Repositories

Please sign up or login with your details

Forgot password? Click here to reset