用于预测演化超图中方向性关系的神经时间点过程
Neural Temporal Point Processes for Forecasting Directional Relations in Evolving Hypergraphs
AI总结：
本文提出一种基于时间点过程的序列生成方法，通过多阶段预测超图中的有向超边，有效缩小指数级搜索空间，在事件类型预测上性能显著提升。
摘要：
在当前的数据和人工智能时代，预测实体之间的关系至关重要。然而，现实世界中的关系本质上具有方向性、涉及两个以上的实体，并且会随时间变化，这一点常常被忽视。在本文中，我们针对在一般设置下预测方向性关系的问题提供了一个全面的解决方案，其中关系是高阶的，即超图中的有向超边。该问题在现有文献中尚未被探索。解决该问题的主要挑战在于，在每个事件时间，可能的超边数量相对于节点数量呈指数级增长。为了克服这一点，我们提出了一种序列生成方法，将预测过程划分为多个阶段，每个阶段依赖于前序阶段，从而缩小超边预测涉及的搜索空间。第一阶段包含一个基于时间点过程的节点事件预测模块，用于识别事件涉及的节点子集。第二阶段是一个候选生成模块，预测超边大小和观察事件的节点的邻接向量。最后阶段是一个有向超边预测器，通过在候选超边集合上进行搜索来识别真实情况。为了验证我们模型的有效性，我们整理了五个数据集，并进行了广泛的实证研究以评估每个下游任务。在事件类型预测方面，我们提出的方法与最先进的成对事件预测模型和超边事件预测模型相比，分别实现了32%和41%的性能提升。
英文摘要：
Forecasting relations between entities is paramount in the current era of data and AI. However, it is often overlooked that real-world relationships are inherently directional, involve more than two entities, and can change with time. In this paper, we provide a comprehensive solution to the problem of forecasting directional relations in a general setting, where relations are higher-order, i.e., directed hyperedges in a hypergraph. This problem has not been previously explored in the existing literature. The primary challenge in solving this problem is that the number of possible hyperedges is exponential in the number of nodes at each event time. To overcome this, we propose a sequential generative approach that segments the forecasting process into multiple stages, each contingent upon the preceding stages, thereby reducing the search space involved in predictions of hyperedges. The first stage involves a temporal point process-based node event forecasting module that identifies the subset of nodes involved in an event. The second stage is a candidate generation module that predicts hyperedge sizes and adjacency vectors for nodes observing events. The final stage is a directed hyperedge predictor that identifies the truth by searching over the set of candidate hyperedges. To validate the effectiveness of our model, we compiled five datasets and conducted an extensive empirical study to assess each downstream task. Our proposed method achieves a performance gain of 32\% and 41\% compared to the state-of-the-art pairwise and hyperedge event forecasting models, respectively, for the event type prediction.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
