Knowledge Graph Model Research Articles

Tensor decompositions for temporal knowledge graph completion with time perspective

Facts in the real world are often tied to time, such as the spread of diseases, and the state of military affairs. Therefore, knowledge graphs combined with temporal factors have gained growing attention. In the temporal knowledge graph, most researchers focus on the original facts and pay attention to their changes over time. The temporal factors are only used as auxiliary information for representation learning. In this paper, we try to observe from the perspective of time and find some interesting properties of temporal knowledge graph: (1) Simultaneousness. Various facts occur at the same time; (2) Aggregation. The facts may aggregately occur for a certain individual, organization, or location; (3) Associativity. Some specific relations tend to occur at specific times, such as celebrations at festivals. Based on the above three properties, we add a simple time-aware module to the existing tensor decomposition-based temporal knowledge graph model TComplEx (Lacroix et al., 2020), which obtains impressive improvements and achieves state-of-the-art results on four standard temporal knowledge graph completion benchmarks. Specifically, in terms of mean reciprocal rank (MRR), we advance the state-of-the-art by ＋24.0% on ICEWS14, ＋13.2% on ICEWS05-15, ＋31.9% on YAGO15k, and 4.7% on GDELT.

Retrieval-Augmented Knowledge Graph Reasoning for Commonsense Question Answering

Existing knowledge graph (KG) models for commonsense question answering present two challenges: (i) existing methods retrieve entities related to questions from the knowledge graph, which may extract noise and irrelevant nodes, and (ii) there is a lack of interaction representation between questions and graph entities. However, current methods mainly focus on retrieving relevant entities with some noisy and irrelevant nodes. In this paper, we propose a novel retrieval-augmented knowledge graph (RAKG) model, which solves the above issues using two key innovations. First, we leverage the density matrix to make the model reason along the corrected knowledge path and extract an enhanced subgraph of the knowledge graph. Second, we fuse representations of questions and graph entities through a bidirectional attention strategy, in which two representations fuse and update using a graph convolutional network (GCN). To evaluate the performance of our method, we conducted experiments on two widely used benchmark datasets: CommonsenseQA and OpenBookQA. The case study gives insight into the finding that the augmented subgraph provides reasoning along the corrected knowledge path for question answering.

Application of an in silico approach identifies a genetic locus within ITGB2, and its interactions with HSPG2 and FGF9, to be associated with anterior cruciate ligament rupture risk

ABSTRACT We developed a Biomedical Knowledge Graph model that is phenotype and biological function-aware through integrating knowledge from multiple domains in a Neo4j, graph database. All known human genes were assessed through the model to identify potential new risk genes for anterior cruciate ligament (ACL) ruptures and Achilles tendinopathy (AT). Genes were prioritised and explored in a case–control study comparing participants with ACL ruptures (ACL-R), including a sub-group with non-contact mechanism injuries (ACL-NON), to uninjured control individuals (CON). After gene filtering, 3376 genes, including 411 genes identified through previous whole exome sequencing, were found to be potentially linked to AT and ACL ruptures. Four variants were prioritised: HSPG2:rs2291826A/G, HSPG2:rs2291827G/A, ITGB2:rs2230528C/T and FGF9:rs2274296C/T. The rs2230528 CC genotype was over-represented in the CON group compared to ACL-R (p < 0.001) and ACL-NON (p < 0.001) and the TT genotype and T allele were over-represented in the ACL-R group and ACL-NON compared to CON (p < 0.001) group. Several significant differences in distributions were noted for the gene-gene interactions: (HSPG2:rs2291826, rs2291827 and ITGB2:rs2230528) and (ITGB2:rs2230528 and FGF9:rs2297429). This study substantiates the efficiency of using a prior knowledge-driven in silico approach to identify candidate genes linked to tendon and ACL injuries. Our biomedical knowledge graph identified and, with further testing, highlighted novel associations of the ITGB2 gene which has not been explored in a genetic case control association study, with ACL rupture risk. We thus recommend a multistep approach including bioinformatics in conjunction with next generation sequencing technology to improve the discovery potential of genomics technologies in musculoskeletal soft tissue injuries. Highlights A biomedical knowledge graph was modelled for musculoskeletal soft tissue injuries to efficiently identify candidate genes for genetic susceptibility analyses. The biomedical knowledge graph and sequencing data identified potential biologically relevant variants to explore susceptibility to common tendon and ligament injuries. Specifically genetic variants within the ITGB2 and FGF9 genes were associated with ACL risk. Novel allele combinations (HSPG2-ITGB2 and ITGB2-FGF9) showcase the potential effect of ITGB2 in influencing risk of ACL rupture.

A graph database for life cycle inventory using Neo4j

Life cycle inventory (LCI) databases constitute the basis for the life cycle assessment (LCA) of a product system. LCI data involve complex relationships between the production activities and the environment. The currently used relational database employs a rigid schema structure of two-dimensional tables and lacks direct support for the complex relationships between LCI data. In this paper, a graph database was designed and constructed using Neo4j graph database management system. First, an LCI knowledge graph (LCIKG) model for the graph database is proposed, which employs the labeled property graph structure and describes the LCI data and the semantic relationships among LCI data concepts. Second, Ecoinvent datasets were successfully used to construct the LCI graph database by automatically extracting Cypher syntax patterns; then, Neo4j was used to store, visualize, and retrieve LCI data. Finally, a set of queries have been executed to evaluate the performance of the graph database; a case study has been provided to demonstrate the effectiveness of the proposed graph database. The graph database can effectively reduce the time and effort to query and process LCI data of a product system. Moreover, the dynamic schema of the LCIKG model promotes the scalability and interoperability of LCI data. The completed work provides a feasible solution for the issues and challenges in current LCI research and promotes the wide application of LCA.

Research on unbalanced mining of highway project key data based on knowledge graph and cloud model

Various stages of highway project construction process involve text, image, audio, video and other related data sources involving many participants, forming a huge amount of data. Accurately tracing the source of responsibility, refining and applying the unbalanced data in the highway project archives is of great significance for realizing the intelligent transformation of highway construction project management. This paper firstly sorts out the construction process of highway projects and the main data sources, constructs a data association network between construction entities and construction process, as well as a knowledge map of highway construction data. Then, according to the highway construction stage, an index system based on 12 key data is constructed by using the entropy weight cloud model method, and the importance of the data is evaluated. Thirdly, based on the unbalanced characteristics of highway project data, a method of mining big data in highway project archives using classification evaluation indexes is proposed, and the accuracy of this method is verified by case calculation. Finally, taking the Shizong Qiubei Expressway in China as an example, the intelligent management and control suggestions for key data of transportation projects are proposed. It is found that the key data with special importance rate in highway construction include construction data, supervision data and completion data. Boosting algorithm is more accurate than the traditional SMOTE algorithm for unbalanced data mining, which helps to save the project construction cost and improve the quality of data extraction in the project archives. This study provides a theoretical reference for key data traceability of highway project intelligent management and control platform and the improvement of intelligent management efficiency.

Extraction of knowledge graph of Covid-19 through mining of unstructured biomedical corpora

The number of biomedical articles published is increasing rapidly over the years. Currently there are about 30 million articles in PubMed and over 25 million mentions in Medline. Among these fundamentals, Biomedical Named Entity Recognition (BioNER) and Biomedical Relation Extraction (BioRE) are the most essential in analysing the literature. In the biomedical domain, Knowledge Graph is used to visualize the relationships between various entities such as proteins, chemicals and diseases. Scientific publications have increased dramatically as a result of the search for treatments and potential cures for the new Coronavirus, but efficiently analysing, integrating, and utilising related sources of information remains a difficulty. In order to effectively combat the disease during pandemics like COVID-19, literature must be used quickly and effectively. In this paper, we introduced a fully automated framework consists of BERT-BiLSTM, Knowledge graph, and Representation Learning model to extract the top diseases, chemicals, and proteins related to COVID-19 from the literature. The proposed framework uses Named Entity Recognition models for disease recognition, chemical recognition, and protein recognition. Then the system uses the Chemical - Disease Relation Extraction and Chemical - Protein Relation Extraction models. And the system extracts the entities and relations from the CORD-19 dataset using the models. The system then creates a Knowledge Graph for the extracted relations and entities. The system performs Representation Learning on this KG to get the embeddings of all entities and get the top related diseases, chemicals, and proteins with respect to COVID-19.

Group Intelligence Recommendation System based on Knowledge Graph and Fusion Recommendation Model

Group Intelligence Recommendation System based on Knowledge Graph and Fusion Recommendation Model

Learning Path Planning Based on Knowledge Graph on MOOC Platform

Based on the edX platform, this paper designs the knowledge graph model by combining expert method and reference method, selects Neo4j as the knowledge storage database of knowledge graph; selects Echarts as the visualization tool of Neo4j, and finally realizes the visual search and display of knowledge points on MOOC platform, and gives learning feedback and update according to the learning situation of learners. When planning the learning path through the designed knowledge graph, Ripplenet algorithm is introduced to enrich the diversity of courses in the learning path planning between courses. Professional learning path planning is provided for learners to improve the learning efficiency of online learning.

Wikidata and knowledge graphs in practice: Using semantic SEO to create discoverable, accessible, machine-readable definitions of the people, places, and services in Libraries and Archives

Libraries expand the access and visibility of data and research in support of an informed public. Search engines have limited knowledge of the dynamic nature of libraries - their people, their services, and their resources. The very definition of libraries in online environments is outdated and misleading. This article offers a solution to this metadata problem by redefining libraries for Machine Learning environments and search engines. Two ways to approach this problem include implementing local structured data in a knowledge graph model and “inside-out” definitions in Semantic Web endpoints. MSU Library has found that implementing a “Knowledge Graph” linked data model leads to improved discovery and interpretation by the bots and search engines that index and describe what libraries are, what they do, and their scholarly content. In contrast, LSE Library has found that contributing to Wikidata, a collaborative and global metadata source, can increase understanding of libraries and extend their reach and engagement. This article demonstrates that Wikidata can be used to push out data, the technical details of knowledge graph markup, and the practice of semantic Search Engine Optimization (SEO). It explores how metadata can represent an organization equitably and how this improves the reach of global information communities.

DRGCNCDA: Predicting circRNA-disease interactions based on knowledge graph and disentangled relational graph convolutional network.

Emerging studies have shown that circular RNA (circRNA) plays a significant role in the diagnosis and prognosis of human disease. Some computational methods have been proposed to predict circRNA-disease associations. However, some methods only use circRNA-disease association and ignore the associations of other biological entities. In addition, these methods do not take into account the latent factors of different kinds of circRNAs and diseases. To solve these limitations of existing computational models, we propose a new computational model (DRGCNCDA) based on disentangled relational graph convolutional network. The circRNA-disease multi-relational graphs are constructed by collecting multiple relational data among circRNA, disease, miRNA and lncRNA. Then, the disentangled relational graph convolutional network is employed to obtain the feature vectors of circRNA and disease. Finally, knowledge graph model is applied to predict the affinity scores of circRNA-disease associations based on the embeddings of circRNA and disease. The 5-fold cross validation is utilized to evaluate the performance of the method. The experimental results show that the DRGCNCDA outperforms other existing models. Moreover, the case study demonstrates that the DRGCNCDA is effective to predict the circRNA-disease association and can provide reliable candidates for biological experiments.

Research on Personalized Learning Resource Recommendation Based on Knowledge Graph Technology

In the face of the dilemma of learners' "learning loss" and "information overload" in information resources, a personalized learning resource recommendation algorithm is proposed by conducting in-depth and extensive research on the knowledge graph. This algorithm relies on the similarity or correlation between learners' characteristics and course knowledge (learning resources) for recommendation. It analyzes learners' characteristics in depth from four aspects: data collection and processing, model construction, resource and path recommendation, and model application, and establishes a multi layered dynamic feature model for learners; Analyze the core elements of the curriculum knowledge graph, decompose the curriculum knowledge into nanoscale knowledge granularity, and construct a curriculum knowledge graph model. The experimental results indicate that this algorithm improves learners' learning efficiency and promotes their personalized development

EAGS: An extracting auxiliary knowledge graph model in multi-turn dialogue generation.

Multi-turn dialogue generation is an essential and challenging subtask of text generation in the question answering system. Existing methods focused on extracting latent topic-level relevance or utilizing relevant external background knowledge. However, they are prone to ignore the fact that relying too much on latent aspects will lose subjective key information. Furthermore, there is not so much relevant external knowledge that can be used for referencing or a graph that has complete entity links. Dependency tree is a special structure that can be extracted from sentences, it covers the explicit key information of sentences. Therefore, in this paper, we proposed the EAGS model, which combines the subjective pivotal information from the explicit dependency tree with sentence implicit semantic information. The EAGS model is a knowledge graph enabled multi-turn dialogue generation model, and it doesn’t need extra external knowledge, it can not only extract and build a dependency knowledge graph from existing sentences, but also prompt the node representation, which is shared with Bi-GRU each time step word embedding in node semantic level. We store the specific domain subgraphs built by the EAGS, which can be retrieved as external knowledge graph in the future multi-turn dialogue generation task. We design a multi-task training approach to enhance semantics and structure local feature extraction, and balance with the global features. Finally, we conduct experiments on Ubuntu large-scale English multi-turn dialogue community dataset and English Daily dialogue dataset. Experiment results show that our EAGS model performs well on both automatic evaluation and human evaluation compared with the existing baseline models.

Opening Knowledge Graph Model Building of Artificial Intelligence Curriculum

The knowledge points setting of artificial intelligence curriculum has shortcomings in connection between theory and practices. To overcome the problem, this study designs an open knowledge point design model based on knowledge graph. Fist, to promote the construction of the knowledge graph (KG) of curriculums, associated teaching research was analyzed visually. Then the order and hierarchical structure of the knowledge points were defined, and the ontology structure of curriculum knowledge and the relationship between knowledge points and posts were designed as well. Moreover, an overall logic structure for the construction of the open KG of curriculums was proposed. Results demonstrated that high attention should be paid to the construction and concern of teaching teams for artificial intelligence algorithms and the KG of curriculum construction. Additionally, the opening model can strengthen the openness of the KG of curriculums to reinforce the close connections between classroom knowledge and practices. Research conclusions are conducive to understand the existing problems in the KG of curriculums and provide beneficial references to the integration of information technology and education.

Knowledge graph model development for knowledge discovery in dementia research using cognitive scripting and next-generation graph-based database: a design science research approach

Recent studies report doubling numbers of deaths due to dementia. With such an escalating mortality rate related to cognitive decline diseases, like dementia, timely information on contributing factors and knowledge discovery from evidence-based repositories is warranted. A large amount of scholarly knowledge extracted from research findings on dementia can be understood only using human intelligence for arriving at quality inferences. Due to the unstructured data presented in such a massive dataset of scientific articles available online, gaining insights from the knowledge hidden in the literature is complex and time-consuming. Hence, there is a need for developing a knowledge management model to create, query and maintain a knowledge repository of key elements and their relationships extracted from scholarly articles in a structured manner. In this paper, an innovative knowledge discovery computing model to process key findings from unstructured data from scholarly articles by using the design science research (DSR) methodology is proposed. The solution caters to a novel composition of the cognitive script of crucial knowledge related to dementia and its subsequent transformation from unstructured into a structured format using graph-based next-generation infrastructures. The computing model contains three phases to assist the research community to have a better understanding of the related knowledge in the existing unstructured research articles: (i) article collection and construction of cognitive script, (ii) generation of Cypher statements (a knowledge graph query language) and (iii) creation of graph-based repository and visualization. The performance of the computing model is demonstrated by visualizing the outcome of various search criteria in the form of nodes and their relationships. Our results also demonstrate the effectiveness of visual query and navigation highlighting its usability.

Adaptive Attentional Network for Few-Shot Relational Learning of Knowledge Graphs

Few-shot knowledge graph reasoning is a research focus in the field of knowledge graph reasoning. At present, in order to expand the application scope of knowledge graphs, a large number of researchers are devoted to the study of the multi-shot knowledge graph model. However, as far as we know, the knowledge graph contains a large number of missing relations and entities, and there are not many reference examples at the time of training. In this paper, our goal is to be able to infer the correct entity given a few training instances, or even only one training instance is available. Therefore, we propose an adaptive attentional network for few-shot relational learning of knowledge graphs, extracting knowledge based on traditional embedding methods, using the Transformer mechanism and hierarchical attention mechanism to obtain hidden attributes of entities, and then using a noise checker to filter out unreasonable candidate entities. Our model produces large performance improvements on the NELL-One dataset.

Research on the construction of smart care question answering system based on knowledge graph

With the deepening of aging in China, the demand of intelligent care system for the elderly is increasing day by day. The rapid development of information technology and artificial intelligence technology have gradually promoted the transformation of traditional care services from artificial to intelligent. Based on knowledge graph technology, this study built a knowledge graph model for elderly chronic disease smart care. The specific process includes ontology design, knowledge extraction, knowledge graph construction and question answering system design. The uniqueness of the knowledge graph in this paper is that it uses specific information about the elderly and data from professional care books. It is well guaranteed in practicality and reliability.With the help of the knowledge map constructed in this paper, primary care staff can effectively query high-quality and customized chronic disease care knowledge.

CSKG4APT: A Cybersecurity Knowledge Graph for Advanced Persistent Threat Organization Attribution

Open-source cyber threat intelligence (OSCTI) is becoming more influential in obtaining current network security information. Most studies on cyber threat intelligence (CTI) focus on automating the extraction of threat entities from public sources that describe attack events. The cybersecurity knowledge graph aims to change the expression of threat knowledge so that security researchers can accurately and efficiently obtain various types of threat information for preliminary intelligent decisions. The attribution technology can not only assist security analysts in detecting advanced persistent threats, but can also identify the same threat from different attack events. Therefore, it is important to trace the attack threat actor. In this study, we used the knowledge graph technology, considered the latest research on cyber threat attack attribution, and thoroughly examined key related technologies and theories in the process of constructing and applying the advanced persistent threat (APT) knowledge graph from OSCTI. We designed a cybersecurity platform named CSKG4APT based on a knowledge graph. Inspired by the theory of ontology, we constructed CSKG4APT as an APT knowledge graph model based on real APT attack scenarios. We then designed an APT threat knowledge extraction algorithm for completing and updating the knowledge graph using deep learning and expert knowledge. Finally, we proposed a practical APT attack attribution method with attribution and countermeasures. CSKG4APT is not a passive defense method in traditional network confrontation but one that integrates a large amount of fragmented intelligence and can actively adjust its defense strategy. It lays the foundation for further dominance in network attack and defense.

An approach to capturing and reusing tacit design knowledge using relational learning for knowledge graphs

Tacit design knowledge plays an important role in the process of product design and is a valuable knowledge asset for enterprises. In terms of the characteristics of tacit rational design knowledge, this paper puts forward a scientific hypothesis and approach on capturing and reusing tacit rational design knowledge. The presented approach represents the observable design result facts of products using design knowledge graphs. A design issue-solving oriented knowledge graph model is presented, where directed relation edges represent design issues, and nodes stand for design solutions. When a new design solutions requirement needs to be searched, tacit design knowledge can be reused by relational learning for the constructed design knowledge graphs. In relational learning, the design knowledge graph is converted into a three-order tensor, where two modes are solution nodes, and the third mode holds the issue relations. Then, a tensor factorization approach is employed to calculate the latent features between design solutions for an issue relation. As a result, a score vector to represent the existence of issue-solution relations can be obtained. By sorting the scores in descending order, we may select the solution node with the highest score as the design solution to be searched. Finally, a stamping die design case study is provided. The case study shows that the proposed approach is feasible, and effective, and has better flexibility, scalability and efficiency than CBR methods.

From social networks to knowledge graphs: A plea for interdisciplinary approaches

Contextual information is a crucial factor in interdisciplinary research on social networks. At the same time, missing linked data and missing methods for large-scale knowledge networks are a serious limitation. Only few researches have addressed the questions between data science, graph theory and social network analysis. This paper seeks to discuss how this gap can be closed. For this, we use an interdisciplinary approach trying to improve the interdisciplinary exchange and method exchange. We investigate how new methods from computer science, in particular knowledge graphs, can be used within the field of SNA. The contributions of this paper are (1) a knowledge graph model representation of a multi-layer social network, (2) the showcase of examples from different domains and (3) a perspective for more interdisciplinary discussion. We present an innovative solution to discuss coming challenges in SNA with methods from the digital humanities, in particular computer science.

Research on Data Mining of Intelligent Education Evaluation from the Perspective of the Knowledge Graph

The continuous development of Internet information technology given birth to data mining technology. Data mining is applied to analyze the internal relationships of data and provides a more optimized advancement way. The paper focuses on how to improve the data mining and analysis capabilities of intelligent education to associate students of the same characteristics. A cluster analysis method was utilized to construct a students’ knowledge graph model, which used a text classification algorithm to classify the evaluation questions and attribute them into various knowledge points. On the basis of the analysis on the data generated from online education, the clustering algorithm was adopted to classify the learning characteristics of the students. A knowledge graph developed by associating the students with similar characteristics was visualized be means of information technology in order to realize visualized and intelligent teaching.