LGIRApr 15, 2023

Temporal Aggregation and Propagation Graph Neural Networks for Dynamic Representation

arXiv:2304.07503v121 citationsh-index: 67Has Code
Originality Incremental advance
AI Analysis

This addresses the challenge of efficient and accurate dynamic representation learning for temporal graphs, which is incremental as it builds on prior graph neural network approaches.

The paper tackles the problem of generating dynamic representations for temporal graphs by proposing TAP-GNN, which uses the whole temporal neighborhood to improve performance and reduce online inference latency, achieving significant gains over existing methods.

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 \url{https://github.com/doujiang-zheng/TAP-GNN}.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes