Figure 2 - uploaded by Feng Xia
Content may be subject to copyright.
Source publication
Contexts in source publication
Context 1
... provides open API and allows integration into other environments for information sharing. Figure 2 presents some of the main components of Web of Scholars: 1) The Profile Search formulates queries of scholars including simple queries and intelligent queries. 2) The Academic Rank is responsible for retrieving scholars in a descending order from the database under different categories. ...
Context 2
... co-author relationship includes three types of networks: ego-center collaboration network, the geographic distribution of collaborators, and changes of collaborator counts over time. We first extract all co-authors of the scholar í µí± from his/her publication metadata, then compute the times of collaborator relationship between them which can be represented by line thickness as shown in Figure 2. ...
Similar publications
Data imbalance is easily found in annotated data when the observations of certain continuous label values are difficult to collect for regression tasks. When they come to molecule and polymer property predictions, the annotated graph datasets are often small because labeling them requires expensive equipment and effort. To address the lack of examp...
For a simple graph with vertex set {v 1 , v 2 ,. .. , v n } and degree sequence d v i i = 1, 2,. .. , n. The inverse sum indeg matrix (ISI-matrix) A ISI (G) = (a ij) of G is a square matrix of order n, where a ij = dv i dv j dv i +dv j , if v i is adjacent to v j and 0, otherwise. The multiset of eigenvalues τ 1 ≥ τ 2 ≥ · · · ≥ τ n of A ISI (G) is...
UDC 512.5 In this paper, we investigate the problem of covering the vertices of a graph associated to a finite vector space as introduced by Das [Commun. Algebra, 44 , 3918 – 3926 (2016)], such that we can uniquely identify any vertex by examining the vertices that cover it. We use locating-dominating sets and identifying codes, which are closely r...
![Cocktail party graphs K2×2\documentclass[12pt]{minimal}...](publication/365968649/figure/fig1/AS:11431281114343803@1674442100755/Cocktail-party-graphs-K22documentclass12ptminimal-usepackageamsmath_Q320.jpg)
![Friendship graphs F2\documentclass[12pt]{minimal} \usepackage{amsmath}...](publication/365968649/figure/fig2/AS:11431281114339811@1674442100897/Friendship-graphs-F2documentclass12ptminimal-usepackageamsmath_Q320.jpg)
![The graphs Gi\documentclass[12pt]{minimal} \usepackage{amsmath}...](publication/365968649/figure/fig3/AS:11431281114339812@1674442100966/The-graphs-Gidocumentclass12ptminimal-usepackageamsmath-usepackagewasysym_Q320.jpg)
The energy of a graph G, denoted by \({\mathcal {E}} (G)\), is defined as the sum of the absolute values of all eigenvalues of G. In this paper, we present new lower bounds for the energy. Moreover, we improve some previous well-known bounds.
Citations
... Within these triples, denoted as (h, r, t), KGs portray relationships (r) between a head entity (h) and a tail entity (t). Quantities of factual triples in various domains, such as e-commerce [1], finance [2], and social networks [3], have served as a valuable resource for numerous downstream KG applications, including triple classification [4], question answering [5], and recommender systems [6]. Due to the inherent incompleteness of knowledge graphs and the high cost associated with manually identifying all factual triples, considerable attention has been placed on advancing automated methods for knowledge graphs completion (KGC). ...
... With the increasing number of scientific publications, including those in the AI domain, many researchers have turned their attention to constructing academic KGs [73], [74], [75], [76]. For example, Färber [74] proposed the Microsoft Academic Knowledge Graph (MAKG), which contains over eight billion triples of information about scientific publications and related entities, such as authors, institutions, journals, and fields of study. ...
AI applications often use ML/DL (Machine Learning/Deep Learning) models to implement specific AI tasks. As application developers usually are not AI experts, they often choose to integrate existing implementations of ML/DL models as libraries for their AI tasks. As an active research area, AI attracts many researchers and produces a lot of papers every year. Many of the papers propose ML/DL models for specific tasks and provide their implementations. However, it is not easy for developers to find ML/DL libraries that are suitable for their tasks. The challenges lie in not only the fast development of AI application domains and techniques, but also the lack of detailed information of the libraries such as environmental dependencies and supporting resources. In this paper, we conduct an empirical study on ML/DL library seeking questions on Stack Overflow to understand the developers' requirements for ML/DL libraries. Based on the findings of the study, we propose a task-oriented ML/DL library recommendation approach, called MLTaskKG. It constructs a knowledge graph that captures AI tasks, ML/DL models, model implementations, repositories, and their relationships by extracting knowledge from different sources such as ML/DL resource websites, papers, ML/DL frameworks, and repositories. Based on the knowledge graph, MLTaskKG recommends ML/DL libraries for developers by matching their requirements on tasks, model characteristics, and implementation information. Our evaluation shows that 92.8% of the tuples sampled from the resulting knowledge graph are correct, demonstrating the high quality of the knowledge graph. A further experiment shows that MLTaskKG can help developers find suitable ML/DL libraries using 47.6% shorter time and with 68.4% higher satisfaction.
... Typically, the knowledge is imported from structured sources by employing mapping languages, such as R2RML (Rodriguez-Muro and Rezk 2015). Furthermore, the knowledge could be extracted from unstructured documents (e.g., news, research papers, and patents) by adopting relation, entity, or attribute extraction methods (Liu et al. 2020;Yu et al. 2020;Yao et al. 2019). ...
With the explosive growth of artificial intelligence (AI) and big data, it has become vitally important to organize and represent the enormous volume of knowledge appropriately. As graph data, knowledge graphs accumulate and convey knowledge of the real world. It has been well-recognized that knowledge graphs effectively represent complex information; hence, they rapidly gain the attention of academia and industry in recent years. Thus to develop a deeper understanding of knowledge graphs, this paper presents a systematic overview of this field. Specifically, we focus on the opportunities and challenges of knowledge graphs. We first review the opportunities of knowledge graphs in terms of two aspects: (1) AI systems built upon knowledge graphs; (2) potential application fields of knowledge graphs. Then, we thoroughly discuss severe technical challenges in this field, such as knowledge graph embeddings, knowledge acquisition, knowledge graph completion, knowledge fusion, and knowledge reasoning. We expect that this survey will shed new light on future research and the development of knowledge graphs.
... Typically, the knowledge is imported from structured sources by employing mapping languages, such as R2RML (Rodriguez-Muro and Rezk, 2015). Furthermore, the knowledge could be extracted from unstructured documents (e.g., news, research papers, and patents) by adopting relation, entity, or attribute extraction methods (Liu et al, 2020;Yu et al, 2020;Yao et al, 2019). ...
With the explosive growth of artificial intelligence (AI) and big data, it has become vitally important to organize and represent the enormous volume of knowledge appropriately. As graph data, knowledge graphs accumulate and convey knowledge of the real world. It has been well-recognized that knowledge graphs effectively represent complex information; hence, they rapidly gain the attention of academia and industry in recent years. Thus to develop a deeper understanding of knowledge graphs, this paper presents a systematic overview of this field. Specifically, we focus on the opportunities and challenges of knowledge graphs. We first review the opportunities of knowledge graphs in terms of two aspects: (1) AI systems built upon knowledge graphs; (2) potential application fields of knowledge graphs. Then, we thoroughly discuss severe technical challenges in this field, such as knowledge graph embeddings, knowledge acquisition, knowledge graph completion, knowledge fusion, and knowledge reasoning. We expect that this survey will shed new light on future research and the development of knowledge graphs.
... Second, multiple resources may also be consider to construct multidimensional recommendations effectively. For example, WoS [115] presented a knowledge graph-based system to extract and rank scholar's profile as well as represents relationships among scholars. A new explicit ranking scheme [113] is proposed that models relatedness of query entity and document entity using the exact match and soft match signals. ...
The necessity for scholarly knowledge mining and management has grown significantly as academic literature and its linkages to authors produce enormously. Information extraction, ontology matching, and accessing academic components with relations have become more critical than ever. Therefore, with the advancement of scientific literature, scholarly knowledge graphs have become critical to various applications where semantics can impart meanings to concepts. The objective of study is to report a literature review regarding knowledge graph construction, refinement and utilization in scholarly domain. Based on scholarly literature, the study presents a complete assessment of current state-of-the-art techniques. We presented an analytical methodology to investigate the existing status of scholarly knowledge graphs (SKG) by structuring scholarly communication. This review paper investigates the field of applying machine learning, rule-based learning, and natural language processing tools and approaches to construct SKG. It further presents the review of knowledge graph utilization and refinement to provide a view of current research efforts. In addition, we offer existing applications and challenges across the board in construction, refinement and utilization collectively. This research will help to identify frontier trends of SKG which will motivate future researchers to carry forward their work.
... At present, numerous awards have been proposed in various scientific disciplines around the world, such as the Fields Medal in mathematics [1] and the Turing Award in computer science [39]. Due to the accessibility of big scholarly data [11,27,38], increasing focus has been placed on exploring how such scientific awards influence the performance and trajectory of the recipients' academic career from different perspectives [25,43]. ...
... The largest existing resource is the crowd-sourced Academic Family Tree (AFT) [6], and the MAG-linked version of which is approximately 180 times smaller than our inferred dataset in terms of the number of mentor-mentee pairs; see Table 1. Other previous work, like SHIFU [7,10,19] built mentorship models using publication information provided by the Microsoft Academic Graph (MAG) [18]. This model was then used to infer mentorship over a part of the MAG (one million authors). ...
Mentorship is a critical component of academia, but is not as visible as publications, citations, grants, and awards. Despite the importance of studying the quality and impact of mentorship, there are few large representative mentorship datasets available. We contribute two datasets to the study of mentorship. The first has 300,000 ground truth academic mentor-mentee pairs obtained from multiple diverse, manually-curated sources, and linked to the Semantic Scholar (S2) knowledge graph. We use this dataset to train an accurate classifier for predicting mentorship relations from bibliographic features, achieving a held-out area under the ROC curve of 0.96. Our second dataset is formed by applying the classifier to the complete co-authorship graph of S2. The result is an inferred graph with 137 million weighted mentorship edges among 24 million nodes. We release this first-of-its-kind dataset to the community to help accelerate the study of scholarly mentorship: \url{https://github.com/allenai/S2AMP-data}
... Knowledge graphs (KG) contains quantities of factual triplets-(head entity, relation, tail entity)-which are widely used in many areas, such as e-commerce [15,16], finance [4,13], and social networks [12,34]. Since knowledge graphs are usually incomplete and manually finding all factual triplets is expensive, how to automatically perform knowledge graph completion (KGC) has attracted great attention. ...
Graph convolutional networks (GCNs) -- which are effective in modeling graph structures -- have been increasingly popular in knowledge graph completion (KGC). GCN-based KGC models first use GCNs to generate expressive entity representations and then use knowledge graph embedding (KGE) models to capture the interactions among entities and relations. However, many GCN-based KGC models fail to outperform state-of-the-art KGE models though introducing additional computational complexity. This phenomenon motivates us to explore the real effect of GCNs in KGC. Therefore, in this paper, we build upon representative GCN-based KGC models and introduce variants to find which factor of GCNs is critical in KGC. Surprisingly, we observe from experiments that the graph structure modeling in GCNs does not have a significant impact on the performance of KGC models, which is in contrast to the common belief. Instead, the transformations for entity representations are responsible for the performance improvements. Based on the observation, we propose a simple yet effective framework named LTE-KGE, which equips existing KGE models with linearly transformed entity embeddings. Experiments demonstrate that LTE-KGE models lead to similar performance improvements with GCN-based KGC methods, while being more computationally efficient. These results suggest that existing GCNs are unnecessary for KGC, and novel GCN-based KGC models should count on more ablation studies to validate their effectiveness. The code of all the experiments is available on GitHub at https://github.com/MIRALab-USTC/GCN4KGC.
... Overall, the research was very helpful in terms of creating an effective bibliometric visualization and examination of JDoc, and it helped to add some interesting topics to LIS to facilitate better connections between contributors. Liu et al., [33] also proposed a new system that used mining techniques called the web of scholars. The model uses methods such as searching, mining, and other complex network visualizations that correspond to scholars from the field of computer science. ...
In this era of digital transformation, when the amount of scholarly literature is rapidly growing, hundreds of papers are published online daily with regard to different fields, especially in relation to academic subjects. Therefore, it difficult to find an expert/author to collaborate with from a specific research area. This is thought to be one of the most challenging activities in academia, and few people have considered authors’ multi-factors as an enhanced method to find potential collaborators or to identify the expert among them; consequently, this research aims to propose a novel model to improve the process of recommending authors. This is based on the authors’ similarity measurements by extracting their explicit and implicit topics of interest from their academic literature. The proposed model mainly consists of three factors: author-selected keywords, the extraction of a topic’s distribution from their publications, and their publication-based statistics. Furthermore, an enhanced approach for identifying expert authors by extracting evidence of expertise has been proposed based on the topic-modeling principle. Subsequently, an interactive network has been constructed that represents the predicted authors’ collaborative relationship, including the top-k potential collaborators for each individual. Three experiments have been conducted on the collected data; they demonstrated that the most influential factor for accurately recommending a collaborator was the topic’s distribution, which had an accuracy rate of 88.4%. Future work could involve building a heterogeneous co-collaboration network that includes both the authors with their affiliations and computing their similarities. In addition, the recommendations would be improved if potential and real collaborations were combined in a single network.
... The second category of datasets is knowledge base of COVID-19, for instance, scholar knowledge graph [36], medical knowledge graph [73]. A part of COVID-19 knowledge bases [46] contain complex contents in datasets, such as text data and image data. ...
The outbreak of the COVID-19 pandemic affects lives and social-economic development around the world. The affecting of the pandemic has motivated researchers from different domains to find effective solutions to diagnose, prevent, and estimate the pandemic and relieve its adverse effects. Numerous COVID-19 datasets are built from these studies and are available to the public. These datasets can be used for disease diagnosis and case prediction, speeding up solving problems caused by the pandemic. To meet the needs of researchers to understand various COVID-19 datasets, we examine and provide an overview of them. We organise the majority of these datasets into three categories based on the category of applications, i.e., time-series, knowledge base, and media-based datasets. Organising COVID-19 datasets into appropriate categories can help researchers hold their focus on methodology rather than the datasets. In addition, applications and COVID-19 datasets suffer from a series of problems, such as privacy and quality. We discuss these issues as well as potentials of COVID-19 datasets.
