Collaborator recommendation is of great significance for facilitating research collaboration. Proximities have been demonstrated to be significant factors and determinants of research collaboration. Research leadership is associated with not only the capability to integrate resources to launch and sustain the research project but also the production and academic impact of the collaboration team. However, existing studies mainly focus on social or cognitive proximity, failing to integrate critical proximities comprehensively. Besides, existing studies focus on recommending relationships among all the coauthors, ignoring leadership in research collaboration. In this article, we propose a proximity-aware research leadership recommendation (PRLR) model to systematically integrate critical node attribute information (critical proximities) and network features to conduct research leadership recommendation by predicting the directed links in the research leadership network. PRLR integrates cognitive, geographical, and institutional proximity as node attribute information and constructs a leadership-aware coauthorship network to preserve the research leadership information. PRLR learns the node attribute information, the local network features, and the global network features with an autoencoder model, a joint probability constraint, and an attribute-aware skip-gram model, respectively. Extensive experiments and ablation studies have been conducted, demonstrating that PRLR significantly outperforms the state-of-the-art collaborator recommendation models in research leadership recommendation.

中文翻译：

---

通过深度神经网络进行研究协作中的邻近感知研究领导力推荐

合作者推荐对于促进研究合作具有重要意义。已证明邻近是研究合作的重要因素和决定因素。研究领导力不仅与整合资源以启动和维持研究项目的能力有关，而且与合作团队的生产和学术影响有关。然而，现有的研究主要集中在社会或认知邻近，未能全面整合关键邻近。此外，现有研究侧重于推荐所有合著者之间的关系，而忽略了研究合作中的领导力。在本文中，我们提出了一种邻近感知研究领导力推荐（PRLR）模型，通过预测研究领导力网络中的有向链接，系统地整合关键节点属性信息（关键邻近度）和网络特征来进行研究领导力推荐。PRLR 将认知、地理和机构邻近度作为节点属性信息，构建领导力感知的合着网络来保存研究领导力信息。PRLR 分别使用自动编码器模型、联合概率约束和属性感知跳过语法模型来学习节点属性信息、局部网络特征和全局网络特征。已经进行了广泛的实验和消融研究，