在具有双线性交互的动态图中学习时间注意
Learning Temporal Attention in Dynamic Graphs with Bilinear Interactions
摘要：
在生物信息学、物理学和社交网络等许多领域，关于图随时间演化的推理是一个具有挑战性的概念。我们考虑一种常见的情况，其中边缘可以是短期相互作用（例如，消息传送）或长期结构连接（例如，友谊）。在实践中，长期边缘通常由人类指定。人工指定的边的产生成本很高，而且对于下游任务来说是次优的。为了缓解这些问题，我们提出了一个基于时间点过程和变分自编码器的模型，该模型通过观察节点通信来学习推断节点之间的时间注意力。由于时间注意力驱动节点之间的特征传播，因此使用节点交互的动态来学习这个关键组件提供了更大的灵活性，同时避免了与人类指定的边缘相关的问题。我们还提出了一个双线性变换层的节点功能对，而不是串联，通常使用在以前的工作，并证明其优越的性能在所有情况下。在动态链接预测任务中的两个数据集上的实验中，我们的模型通常优于需要人类指定图的基线模型。此外，我们习得的注意力在语义上是可解释的，并推断出类似于实际图形的连接。
英文摘要：
Reasoning about graphs evolving over time is a challenging concept in many domains, such as bioinformatics, physics, and social networks. We consider a common case in which edges can be short term interactions (e.g., messaging) or long term structural connections (e.g., friendship). In practice, long term edges are often specified by humans. Human-specified edges can be both expensive to produce and suboptimal for the downstream task. To alleviate these issues, we propose a model based on temporal point processes and variational autoencoders that learns to infer temporal attention between nodes by observing node communication. As temporal attention drives between-node feature propagation, using the dynamics of node interactions to learn this key component provides more flexibility while simultaneously avoiding issues associated with human-specified edges. We also propose a bilinear transformation layer for pairs of node features instead of concatenation, typically used in prior work, and demonstrate its superior performance in all cases. In experiments on two datasets in the dynamic link prediction task, our model often outperforms the baseline model that requires a human-specified graph. Moreover, our learned attention is semantically interpretable and infers connections similar to actual graphs.
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。
