Academic networks in the real world can usually be described by heterogeneous information networks composed of multi-type nodes and relationships. Some existing research on representation learning for homogeneous information networks lacks the ability to explore heterogeneous information networks in heterogeneous information networks. It cannot be applied to heterogeneous information networks. Aiming at the practical needs of effectively identifying and discovering scientific research teams from the academic heterogeneous information network composed of massive and complex scientific and technological big data, this paper proposes a scientific research team identification method based on representation learning of academic heterogeneous information networks. The attention mechanism at node level and meta-path level learns low-dimensional, dense and real-valued vector representations on the basis of retaining the rich topological information of nodes in the network and the semantic information based on meta-paths, and realizes effective identification and discovery of scientific research teams and important team members in academic heterogeneous information networks based on maximizing node influence. Experimental results show that our proposed method outperforms the comparative methods.

翻译：现实世界中的学术网络通常可由多类节点和关系组成的异质信息网络描述。现有一些面向同质信息网络的表示学习研究缺乏对异质信息网络中异构信息的挖掘能力，无法直接应用于异质信息网络。针对从海量复杂科技大数据构成的学术异质信息网络中有效识别与发现科研团队的实际需求，本文提出一种基于学术异质信息网络表示学习的科研团队识别方法。该方法通过节点级和元路径级注意力机制，在保留网络中节点丰富拓扑信息及基于元路径的语义信息基础上，学习低维稠密的实值向量表示，并基于最大化节点影响力实现学术异质信息网络中科研团队及重要团队成员的识别发现。实验结果表明，本文提出的方法优于对比方法。