Collaborator recommendation integrating author’s cooperation strength and research interests on attributed graph

Collaborator recommendation aims to seek suitable collaborators for a given author. In this paper, we model all authors and their features as an attributed graph, and then perform community search on the attributed graph to locate the best collaborator community. From the early collaborative filtering-based methods to the recent deep learning-based methods, most existing works usually unilaterally weigh the network structure or node attributes, or directly search the community via the given node. We argue that the inherent disadvantage of these methods is that the quality of the node to be recommended may not be high, which can lead to suboptimal recommendation results. In this work, we develop a new recommendation framework, i.e., Collaborator Recommendation Integrating Author’s Cooperation Strength and Research Interests (CRISI) on an attributed graph. It improves the quality of recommended node via double-weighting the structure and attributes as well as adopting the node replacement method. This can effectively recommend collaborators who have a close cooperative relationship with the recommended node. We conduct extensive experiments on two real-world datasets, and further analysis shows that the performance of our proposed CRISI model is superior to existing methods.