Abstract
Most of the existing link prediction methods for heterogeneous academic networks can only predict one or two specific relation types rather than arbitrary relation types. Although several recently proposed methods have involved multi-relational prediction problems, they do not comprehensively consider the rich semantic or temporal information of heterogeneous academic networks. Considering that researchers may have diverse requirements for different types of academic resources, in this study, we propose a new unified link prediction framework (UniLPF) for arbitrary types of academic relations. First, a weighted and directed heterogeneous academic network containing rich academic objects and relations is constructed. Then, an automatic meta-path searching method is proposed to extract the meta-paths for arbitrary prediction tasks. Two meta-path based object similarity measures combining temporal information and content relevance are also proposed to measure the features of the meta-paths. Finally, a pervasive link prediction model is built, which can be embodied based on an arbitrarily specified prediction task and the corresponding meta-path features. Extensive experiments for predicting various relation types with practical significance are conducted on a large-scale Microsoft Academic dataset. The experimental results demonstrate that our proposed UniLPF framework can predict arbitrary specified academic relations, and outperforms the comparison methods in terms of F-measure, accuracy, AUC and ROC. In addition, the time scalability experiments prove that UniLPF also achieves good performance for predicting the academic relations over time.
Highlights
With the acceleration of scientific research, online academic resources are exploding, which makes it difficult for researchers to quickly and accurately select papers or authors related to their research work or journals in which to publish their findings
To solve the above problem, we propose a unified link prediction framework, UniLPF, which is built through the following steps: (1) Constructing a weighted and directed heterogeneous academic network for link prediction, which integrates rich academic information, including several common academic objects, all academic relations between the objects and temporal information
EXPERIMENTAL SCHEMES 1) DATASET To evaluate the effectiveness of UniLPF for predicting arbitrary relation types in heterogeneous academic networks, we conduct extensive experiments based on a real dataset obtained from Microsoft Academic during 2001∼2012 in the field of computer science
Summary
With the acceleration of scientific research, online academic resources are exploding, which makes it difficult for researchers to quickly and accurately select papers or authors related to their research work or journals in which to publish their findings. This is especially true for the junior researchers who have less experience. Many public companies, such as Google and Microsoft, have offered academic searching services, none of them are sufficient to meet the. The associate editor coordinating the review of this article and approving it for publication was Chao Tong. Martinez et al [1] reviewed the general-purpose techniques at the heart of the link prediction problem
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
