We present a novel Recurrent Graph Network (RGN) approach for predicting discrete marked event sequences by learning the underlying complex stochastic process. Using the framework of Point Processes, we interpret a marked discrete event sequence as the superposition of different sequences each of a unique type. The nodes of the Graph Network use LSTM to incorporate past information whereas a Graph Attention Network (GAT Network) introduces strong inductive biases to capture the interaction between these different types of events. By changing the self-attention mechanism from attending over past events to attending over event types, we obtain a reduction in time and space complexity from $\mathcal{O}(N^2)$ (total number of events) to $\mathcal{O}(|\mathcal{Y}|^2)$ (number of event types). Experiments show that the proposed approach improves performance in log-likelihood, prediction and goodness-of-fit tasks with lower time and space complexity compared to state-of-the art Transformer based architectures.
翻译:我们提出了一个新的经常性图表网络(RGN)方法,通过学习基本的复杂随机过程来预测离散事件序列。使用点进程框架,我们将一个标记的离散事件序列解释为每个独特类型不同序列的叠加。图形网络的节点使用LSTM来整合过去的信息,而图形关注网络(GAT网络)则引入强烈的感应偏差来捕捉这些不同类型事件之间的互动。通过改变自留机制,从关注过去的事件转为关注事件类型,我们的时间和空间复杂性从$\mathcal{O}(N%2)美元(事件总数)降至$\mathcal{O}(事件类型数目)。实验显示,拟议方法提高了日志相似性、预测和适宜性任务的性,而时间和空间的复杂性则低于以艺术变异器为基础的结构。