Learning Relational Fractals for Deep Knowledge Graph Embedding in Online Social Networks

Knowledge Graphs (KGs) have deep and impactful applications in a wide-array of information networks such as natural language processing, recommendation systems, predictive analysis, recognition, classification, etc. Embedding real-life relational representations in KGs is an essential process of abstracting facts for many important data mining tasks like information retrieval, privacy and control, enrichment and so on. In this paper, we investigate the embedding of the relational fractals which are learned from the Relational Turbulence profiles in the transactions of Online Social Networks (OSNs) into KGs. These relational fractals have the capability of building both compositional-depth hierarchies and shallow-wide continuous vector spaces for more efficient computations on devices with limited resources. The results from our RFT model show accurate predictions of relational turbulence patterns in OSNs which can be used to evolve facts in KGs for more accurate and timely information representations.