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}.

翻译：时序图展现了节点在连续时间内的动态交互，其拓扑结构随时间推移而演变。节点的完整时序邻域揭示了其偏好变化。然而，先前的工作通常为简化而仅使用有限邻域生成动态表示，导致性能不佳且在线推理延迟高。因此，本文提出一种利用完整邻域的时序图卷积新方法，即时序聚合与传播图神经网络（TAP-GNN）。具体而言，我们首先通过消息传递范式展开时序图，分析动态表示问题的计算复杂度。高昂的计算复杂度促使我们设计AP（聚合与传播）模块，该模块显著减少了历史邻域的重复计算。最终TAP-GNN支持图流场景中的在线推理，通过时序激活函数、投影层以及多个AP模块将时序信息融入节点嵌入。在多种真实时序网络上的实验结果表明，我们的TAP-GNN在预测性能和在线推理延迟方面均大幅优于现有时序图方法。我们的代码开源在 \url{https://github.com/doujiang-zheng/TAP-GNN}。