Many tasks in graph machine learning, such as link prediction and node classification, are typically solved by using representation learning, in which each node or edge in the network is encoded via an embedding. Though there exists a lot of network embeddings for static graphs, the task becomes much more complicated when the dynamic (i.e. temporal) network is analyzed. In this paper, we propose a novel approach for dynamic network representation learning based on Temporal Graph Network by using a highly custom message generating function by extracting Causal Anonymous Walks. For evaluation, we provide a benchmark pipeline for the evaluation of temporal network embeddings. This work provides the first comprehensive comparison framework for temporal network representation learning in every available setting for graph machine learning problems involving node classification and link prediction. The proposed model outperforms state-of-the-art baseline models. The work also justifies the difference between them based on evaluation in various transductive/inductive edge/node classification tasks. In addition, we show the applicability and superior performance of our model in the real-world downstream graph machine learning task provided by one of the top European banks, involving credit scoring based on transaction data.

本文提出了一种基于 Temporal Graph Network 的动态网络表示学习的新方法，通过提取因果匿名步的高度自定义的消息生成函数。我们提供了一个基准管道以评估时间网络嵌入，并通过边/节点分类任务的各种传导/归纳检验来证明我们模型的优越性能。此外，我们还展示了我们模型在真实世界的下游图机器学习任务中的适用性和优越性能。

时序图网络嵌入与因果匿名遍历表示