Embedding-Based Recommendations on Scholarly Knowledge Graphs

Abstract

The increasing availability of scholarly metadata in the form of Knowledge Graphs (KG) offers opportunities for studying the structure of scholarly communication and evolution of science. Such KGs build the foundation for knowledge-driven tasks e.g., link discovery, prediction and entity classification which allow to provide recommendation services. Knowledge graph embedding (KGE) models have been investigated for such knowledge-driven tasks in different application domains. One of the applications of KGE models is to provide link predictions, which can also be viewed as a foundation for recommendation service, e.g. high confidence "co-author" links in a scholarly knowledge graph can be seen as suggested collaborations. In this paper, KGEs are reconciled with a specific loss function (Soft Margin) and examined with respect to their performance for co-authorship link prediction task on scholarly KGs. The results show a significant improvement in the accuracy of the experimented KGE models on the considered scholarly KGs using this specific loss. TransE with Soft Margin (TransE-SM) obtains a score of 79.5% Hits@10 for co-authorship link prediction task while the original TransE obtains 77.2%, on the same task. In terms of accuracy and Hits@10, TransE-SM also outperforms other state-of-the-art embedding models such as ComplEx, ConvE and RotatE in this setting. The predicted coauthorship links have been validated by evaluating profile of scholars.

Analysing the evolution of computer science events leveraging a scholarly knowledge graph: a scientometrics study of top-ranked events in the past decade

“…Metadata analyses of scientific events have received much attention in the past decade due to the mega-trend of digitization and the ease of scientific events organization. Several efforts have been made for assessing or tracking the evolution of a specific scientific community by analyzing the metadata of particular event series Aumüller and Rahm (2011); Barbosa et al (2017); Fathalla and Lange (2018); Biryukov and Dong (2010); Fathalla et al (2017Fathalla et al ( , 2018; ; Nayyeri et al (2020). Currently, there are several single sources on scientific events and source-dedicated services available for researchers to explore events and as a channel for event organizers to disseminate information about their event.…”

“…( 2016 ); Nayyeri et al. ( 2020 ). Currently, there are several single sources on scientific events and source-dedicated services available for researchers to explore events and as a channel for event organizers to disseminate information about their event.…”

Link Prediction of Weighted Triples for Knowledge Graph Completion Within the Scholarly Domain

“…The soft margin loss [34] aims at handling noisy negative samples. It adds slack variables (η h,r,t ) to negative samples optimization in order to mitigate the negative effect of false negative samples:…”

HierClasSArt: Knowledge-Aware Hierarchical Classification of Scholarly Articles

“…In [11], the authors propose a soft marginal TransE for performing KG Completion over the scholarly KGs. In another article [12], the authors propose a framework for embedding based recommendations on scholarly KG. More precisely, the study focuses on co-authorship link prediction using soft marginal TransE.…”