当前位置: X-MOL 学术arXiv.cs.SI › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Multi-View Dynamic Heterogeneous Information Network Embedding
arXiv - CS - Social and Information Networks Pub Date : 2020-11-12 , DOI: arxiv-2011.06346
Zhenghao Zhang, Jianbin Huang and Qinglin Tan

Most existing Heterogeneous Information Network (HIN) embedding methods focus on static environments while neglecting the evolving characteristic of realworld networks. Although several dynamic embedding methods have been proposed, they are merely designed for homogeneous networks and cannot be directly applied in heterogeneous environment. To tackle above challenges, we propose a novel framework for incorporating temporal information into HIN embedding, denoted as Multi-View Dynamic HIN Embedding (MDHNE), which can efficiently preserve evolution patterns of implicit relationships from different views in updating node representations over time. We first transform HIN to a series of homogeneous networks corresponding to different views. Then our proposed MDHNE applies Recurrent Neural Network (RNN) to incorporate evolving pattern of complex network structure and semantic relationships between nodes into latent embedding spaces, and thus the node representations from multiple views can be learned and updated when HIN evolves over time. Moreover, we come up with an attention based fusion mechanism, which can automatically infer weights of latent representations corresponding to different views by minimizing the objective function specific for different mining tasks. Extensive experiments clearly demonstrate that our MDHNE model outperforms state-of-the-art baselines on three real-world dynamic datasets for different network mining tasks.

中文翻译:

多视图动态异构信息网络嵌入

大多数现有的异构信息网络(HIN)嵌入方法都专注于静态环境,而忽略了现实世界网络的演变特征。虽然已经提出了几种动态嵌入方法,但它们只是为同构网络设计的,不能直接应用于异构环境。为了应对上述挑战,我们提出了一种将时间信息合并到 HIN 嵌入中的新框架,表示为多视图动态 HIN 嵌入(MDHNE),它可以有效地保留来自不同视图的隐式关系随时间更新节点表示的演化模式。我们首先将 HIN 转换为一系列对应不同视图的同构网络。然后,我们提出的 MDHNE 应用循环神经网络 (RNN) 将复杂网络结构的演化模式和节点之间的语义关系纳入潜在嵌入空间,因此当 HIN 随时间演化时,可以学习和更新来自多个视图的节点表示。此外,我们提出了一种基于注意力的融合机制,它可以通过最小化特定于不同挖掘任务的目标函数来自动推断对应于不同视图的潜在表示的权重。大量实验清楚地表明,我们的 MDHNE 模型在针对不同网络挖掘任务的三个真实世界动态数据集上优于最先进的基线。因此,当 HIN 随时间演变时,可以学习和更新来自多个视图的节点表示。此外,我们提出了一种基于注意力的融合机制,它可以通过最小化特定于不同挖掘任务的目标函数来自动推断对应于不同视图的潜在表示的权重。大量实验清楚地表明,我们的 MDHNE 模型在针对不同网络挖掘任务的三个真实世界动态数据集上优于最先进的基线。因此,当 HIN 随时间演变时,可以学习和更新来自多个视图的节点表示。此外,我们提出了一种基于注意力的融合机制,它可以通过最小化特定于不同挖掘任务的目标函数来自动推断对应于不同视图的潜在表示的权重。大量实验清楚地表明,我们的 MDHNE 模型在针对不同网络挖掘任务的三个真实世界动态数据集上优于最先进的基线。
更新日期:2020-11-13
down
wechat
bug