Limited by the time complexity of querying k-hop neighbors in a graph database, most graph algorithms cannot be deployed online and execute millisecond-level inference. This problem dramatically limits the potential of applying graph algorithms in certain areas, such as financial fraud detection. Therefore, we propose Asynchronous Propagate Attention Network, an asynchronous continuous time dynamic graph algorithm for real-time temporal graph embedding. Traditional graph models usually execute two serial operations: first graph computation and then model inference. We decouple model inference and graph computation step so that the heavy graph query operations will not damage the speed of model inference. Extensive experiments demonstrate that the proposed method can achieve competitive performance and 8.7 times inference speed improvement in the meantime. The source code is published at a Github repository.

中文翻译：

---

APAN：用于实时时间图嵌入的异步传播注意网络

由于在图数据库中查询k-hop邻居的时间复杂度受到限制，大多数图算法无法在线部署并执行毫秒级的推理。这个问题极大地限制了在某些领域中应用图形算法的潜力，例如财务欺诈检测。因此，我们提出了异步传播注意网络，一种用于实时时间图嵌入的异步连续时间动态图算法。传统的图形模型通常执行两个串行操作：首先进行图形计算，然后进行模型推断。我们将模型推论和图形计算步骤解耦，以便繁重的图查询操作不会损害模型推论的速度。大量的实验表明，该方法可以达到良好的竞争性能。同时推理速度提高了7倍。源代码在Github存储库中发布。