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.

Vector representations learning (also known as embeddings) for users (items) are at the core of modern recommendation systems. Existing works usually map users and items to low-dimensional space to predict user preferences for items and describe pre-existing features (such as ID) of users (or items) to obtain the embedding of the user (or item). However, we argue that such methods neglect the dual role of users, side information of users and items (e.g., dual citation relationship of authors, authoritativeness of authors and papers) when recommendation is performed for scientific paper. As such, the resulting representations may be insufficient to predict optimal author citations.In this paper, we contribute a new model named scientific paper recommendation using Author's Dual Role Citation Relationship (ADRCR) to capture authors' citation relationship. Our model incorporates the reference relation between author and author, the citation relationship between author and paper, and the authoritativeness of authors and papers into a unified framework. In particular, our model predicts author citation relationship in each specific class. Experiments on the DBLP dataset demonstrate that ADRCR outperforms state-of-theart recommendation methods. Further analysis shows that modeling the author's dual role is particularly helpful for providing recommendation for sparse users that have very few interactions.