Knowledge Graph Research Articles

Contextual knowledge graph approach to bias-reduced decision support systems

ABSTRACT Recent research shows that automated decision-making systems based on Artificial Intelligence (AI) may lead to perceived unfairness and bias, especially in some sensitive areas. There is no universal debiasing solution for AI applications and systems. This paper proposes a bias-reducing framework based on contextual knowledge graphs for decision-making systems to help analyse and detect potential bias factors during system operation in near-real time. In particular, the contextual knowledge graph is designed to learn the relations between current tasks and corresponding features and explore the correlation among data, context and tasks. Three bias assessment metrics (i.e., label bias, sampling bias and timeliness bias) are proposed to measure, quantify and qualitatively define the bias level for the pre- and post-modelling. The trained model using debiased datasets combines contextual knowledge to support fairer decision-making. Experimental results show that the proposed method is more effective in supporting fairer decision- making than the existing methods.

Task-related network based on meta-learning for few-shot knowledge graph completion

Task-related network based on meta-learning for few-shot knowledge graph completion

Relation correlations-aware graph convolutional network with text-enhanced for knowledge graph embedding

Relation correlations-aware graph convolutional network with text-enhanced for knowledge graph embedding

A bibliometric analysis of acupuncture for cerebral infarction from 1993 to 2023

ObjectiveThis research aims to explore the trends and knowledge domain of acupuncture for cerebral infarction through bibliometrics.MethodsPublications related to acupuncture for cerebral infarction were retrieved from the Web of Science core collection database from 1993 to December 31, 2023. A domain knowledge graph was then constructed using VOSviewer, CiteSpace, GraphPad Prism, and Scimago Graphica.ResultsThe cumulative publication trend shows a steady increase over the years, with China being the most productive country. Notably, Europe exhibits significant close collaboration. Institutional cooperation is primarily observed among Chinese universities specializing in traditional Chinese medicine. Tao Jing is the most prolific author, with his highest number of publications is in “Stroke” journal, and Acupuncture Electro Therapeutics Research is the significant journal. Zhang SH is the most cited author, and Si QM is a prominent author in this field. Rehabilitation treatment after cerebral infarction emerges as a prevalent research focus, with nerve regeneration being a keyword. Long EZ's 1989 paper, published in the journal Stroke, holds significant importance. The prominent papers are Donnan et al. and Wu et al., which covers the following topics: “population-based study,” “Baihui Acupoint,” “memory deficits,” “neurotrophic factor,” and “randomized trial.”ConclusionThis bibliometric analysis of acupuncture for cerebral infarction offers insights into the Web of Science database, delineates a knowledge map of countries, authors, institutions, cited authors, keywords, cited references in the field of acupuncture for cerebral infarction, which has a momentous guiding significance for quickly and accurately positioning the key information in the field.

JobEdKG: An uncertain knowledge graph-based approach for recommending online courses and predicting in-demand skills based on career choices

Modern job markets often require an intricate combination of multi-disciplinary skills or specialist and technical knowledge, even for entry-level positions. Such requirements pose increased pressure on students, new graduates, and job seekers to find suitable sources of information to enhance their employability. Unlike standard competence management systems, this paper presents JobEdKG, which helps job seekers from various backgrounds choose online courses based on their prospective careers in addition to predicting different skills that may be required in their chosen career path. While existing solutions focus on internal institutional data, such as previous student experiences and a fixed set of skills provided by curated datasets, JobEdKG considers external data, recommending online courses that best cover the knowledge and skills required by selected job roles, in addition to extracting and predicting skills of that particular job roles. To achieve this, we first extract skills from job postings and online courses. These skills are linked to job titles, online courses, and other concepts in order to create a knowledge graph (KG). We assign an uncertainty score to each fact in the KG based on the prevalence of the fact in the source data (i.e. job listings and online courses), which results in an uncertain KG (UKG). Finally, we model the constructed UKG in order to infer different relations between the different concepts. The code and the data are available on our GitHub repository (https://github.com/team611/JobEd) and a user interface to browse the KG is available at (http://jobed.datanets.org/).

Elucidating the semantics-topology trade-off for knowledge inference-based pharmacological discovery.

Leveraging AI for synthesizing the deluge of biomedical knowledge has great potential for pharmacological discovery with applications including developing new therapeutics for untreated diseases and repurposing drugs as emergent pandemic treatments. Creating knowledge graph representations of interacting drugs, diseases, genes, and proteins enables discovery via embedding-based ML approaches and link prediction. Previously, it has been shown that these predictive methods are susceptible to biases from network structure, namely that they are driven not by discovering nuanced biological understanding of mechanisms, but based on high-degree hub nodes. In this work, we study the confounding effect of network topology on biological relation semantics by creating an experimental pipeline of knowledge graph semantic and topological perturbations. We show that the drop in drug repurposing performance from ablating meaningful semantics increases by 21% and 38% when mitigating topological bias in two networks. We demonstrate that new methods for representing knowledge and inferring new knowledge must be developed for making use of biomedical semantics for pharmacological innovation, and we suggest fruitful avenues for their development.

An embedding model for temporal knowledge graphs with long and irregular intervals

An embedding model for temporal knowledge graphs with long and irregular intervals

Exploring Large-Scale Financial Knowledge Graph for SMEs Supply Chain Mining

Exploring Large-Scale Financial Knowledge Graph for SMEs Supply Chain Mining

Multi-task Information Enhancement Recommendation model for educational Self-Directed Learning System

In Self-Directed Learning Systems (SDLS), suggesting specific exercises to students after viewing educational videos is crucial, which promotes the integration of learning resources and improves learning efficiency. Given that exercises and educational videos are distinct learning resources, suggesting exercises centered on educational videos containing knowledge concepts is referred to as cross-type recommendations. Traditional cross-type recommendation methods usually separate data representation and recommendation tasks, which hampers effective knowledge transfer and information fusion. Furthermore, educational resources frequently feature an irregular distribution of information, posing a significant challenge to existing models in extracting crucial information. Besides, due to the inadequate data, the cross-type recommendation system needs help in developing a robust model. To address these challenges, we propose a Multi-task Information Enhancement Recommendation (MIER) Model in this paper. This model provides a comprehensive recommendation capability by integrating resource representation and merging recommendations. Multi-task learning improves the capacity to integrate information and transfer knowledge. Then, we propose an Information Enhancement Encoder (IEE) module that utilizes the attention mechanism to enhance the model’s ability to extract essential information from educational videos and exercises. Finally, to address the problem of inadequate data, we design a fusion structure that incorporates the concept knowledge graph as expert information into the model. To evaluate the effectiveness of the MIER, we compare it with other models on both predicting concepts and recommending exercises task. The corresponding results demonstrate that the MIER outperforms all the other models. We comprehensively evaluated the MIER model’s performance across a range of datasets varying in labeled data quantity. The findings demonstrate that the model consistently achieves outstanding performance and exhibits robustness, even under conditions of limited label availability.

The digital lab manager: Automating research support.

Laboratory management automation is essential for achieving interoperability in the domain of experimental research and accelerating scientific discovery. The integration of resources and the sharing of knowledge across organisations enable scientific discoveries to be accelerated by increasing the productivity of laboratories, optimising funding efficiency, and addressing emerging global challenges. This paper presents a novel framework for digitalising and automating the administration of research laboratories through The World Avatar, an all-encompassing dynamic knowledge graph. This Digital Laboratory Framework serves as a flexible tool, enabling users to efficiently leverage data from diverse systems and formats without being confined to a specific software or protocol. Establishing dedicated ontologies and agents and combining them with technologies such as QR codes, RFID tags, and mobile apps, enabled us to develop modular applications that tackle some key challenges related to lab management. Here, we showcase an automated tracking and intervention system for explosive chemicals as well as an easy-to-use mobile application for asset management and information retrieval. Implementing these, we have achieved semantic linking of BIM and BMS data with laboratory inventory and chemical knowledge. Our approach can capture the crucial data points and reduce inventory processing time. All data provenance is recorded following the FAIR principles, ensuring its accessibility and interoperability.

Missing Link Prediction in Art Knowledge Graph using Representation Learning

Knowledge graphs are an important evolving field in Artificial Intelligence domain which has multiple applications such as in question answering, important information retrieval, information recommendation, Natural language processing etc. Knowledge graph has one big limitation i.e. Incompleteness, it is due to because of real world data are dynamic and continues evolving. This incompleteness of Knowledge graph can be overcome or minimized by using representation learning models. There are several models which are classified on the base of translation distance, semantic information and NN (Neural Network) based. Earlier the various embedding models are test on mostly two well-known datasets WN18RR & FB15k-237. In this paper, new dataset i.e. ArtGraph has been utilised for link prediction using representation learning models to enhance the utilization of ArtGraph in various domains. Experimental results shown ConvKB performed better over the other models for link prediction task.

Knowledge-based digital twin system: Using a knowlege-driven approach for manufacturing process modeling

The Knowledge-Based Digital Twin System is a digital twin system developed on the foundation of a knowledge graph, aimed at serving the complex manufacturing process. This system embraces a knowledge-driven modeling approach, aspiring to construct a digital twin model for the manufacturing process, thereby enabling precise description, management, prediction, and optimization of the process. The core of this system lies in the comprehensive knowledge graph that encapsulates all pertinent information about the manufacturing process, facilitating dynamic modeling and iteration through knowledge matching and inference within the knowledge, geometry, and decision model. This approach not only ensures consistency across models but also addresses the challenge of coupling multi-source heterogeneous information, creating a holistic and precise information model. As the manufacturing process deepens and knowledge accumulates, the model's understanding of the process progressively enhances, promoting self-evolution and continuous optimization. The developed knowledge-decision-geometry model acts as the ontological layer within the digital twin framework, laying a foundational conceptual framework for the digital twin of the manufacturing process. Validated on an aero-engine blade production line in a factory, the results demonstrate that the knowledge model, as the core driver, enables continuous self-updating of the geometric model for an accurate depiction of the entire manufacturing process, while the decision model provides deep insights for decision-makers based on knowledge. The system not only effectively controls, predicts, and optimizes the manufacturing process but also continually evolves as the process advances. This research offers a new perspective on the realization of the digital twin for the manufacturing process, providing solid theoretical support with a knowledge-driven approach.

A Joint Communication and Computation Design for Probabilistic Semantic Communications

In this paper, the problem of joint transmission and computation resource allocation for a multi-user probabilistic semantic communication (PSC) network is investigated. In the considered model, users employ semantic information extraction techniques to compress their large-sized data before transmitting them to a multi-antenna base station (BS). Our model represents large-sized data through substantial knowledge graphs, utilizing shared probability graphs between the users and the BS for efficient semantic compression. The resource allocation problem is formulated as an optimization problem with the objective of maximizing the sum of the equivalent rate of all users, considering the total power budget and semantic resource limit constraints. The computation load considered in the PSC network is formulated as a non-smooth piecewise function with respect to the semantic compression ratio. To tackle this non-convex non-smooth optimization challenge, a three-stage algorithm is proposed, where the solutions for the received beamforming matrix of the BS, the transmit power of each user, and the semantic compression ratio of each user are obtained stage by stage. The numerical results validate the effectiveness of our proposed scheme.

Semantic integration of diverse data in materials science: Assessing Orowan strengthening

This study applies Semantic Web technologies to advance Materials Science and Engineering (MSE) through the integration of diverse datasets. Focusing on a 2000 series age-hardenable aluminum alloy, we correlate mechanical and microstructural properties derived from tensile tests and dark-field transmission electron microscopy across varied aging times. An expandable knowledge graph, constructed using the Tensile Test and Precipitate Geometry Ontologies aligned with the PMD Core Ontology, facilitates this integration. This approach adheres to FAIR principles and enables sophisticated analysis via SPARQL queries, revealing correlations consistent with the Orowan mechanism. The study highlights the potential of semantic data integration in MSE, offering a new approach for data-centric research and enhanced analytical capabilities.

Liberate the power of biodiversity literature as FAIR digital objects

Knowledge about biodiversity is largely embedded in a daily growing corpus of over 500 million pages of biodiversity literature that is not machine-actionable. It is thus not open to building a biodiversity knowledge graph, or facilitating the use of artificial intelligence tools. This hinders the completion of a much-needed taxonomic name reference system, prevents the discovery of the biotic interactions underpinning the prediction and understanding of global change trends and consequences, viral spillovers, annotation of genes with their respective phenotypes, and their citations in various domains dealing with biological species such as conservation, agriculture, medicine, life sciences and industry, necessary to achieve the objectives of the Green Deal and address the targets identified in the Global Biodiversity Framework. This Policy Brief highlights key actions that can liberate the scientific data published, exploit their use , promote an enhanced way to publish, and ultimately foster excellence and innovation in biodiversity science, monitoring and conservation.

Modification and completion of geological structure knowledge graph based on pattern matching

As a knowledge representation method, knowledge graph is widely used in intelligent question answering systems and recommendation systems. At present, the research on knowledge graph mainly focuses on information query and retrieval based on knowledge graph. In some domain knowledge graphs, specific subgraph structures (patterns) have specific physical meanings. Aiming at this problem, this paper proposes a method and framework of knowledge graph pattern mining based on gat. Firstly, the patterns with specific physical meaning were transformed into subgraph structures containing topological structures and entity attributes. Secondly, the subgraph structure of the pattern is regarded as the query graph, and the knowledge graph is regarded as the data graph, so that the problem is transformed into an approximate subgraph matching problem. Then, the improved relational graph attention network is used to fuse the adaptive edge deletion mechanism to realize the approximate subgraph matching of subgraph structure and attribute, so as to obtain the best matching subgraph. The proposed method is trained in an end-to-end manner. The approximate subgraph matching is realized on the existing data set, and the research work of key pattern mining of complex geological structure knowledge graph is carried out.

Research on Driving Scenario Knowledge Graphs

Despite the partial disclosure of driving scenario knowledge graphs, they still fail to meet the comprehensive needs of intelligent connected vehicles for driving knowledge. Current issues include the high complexity of pattern layer construction, insufficient accuracy of information extraction and fusion, and limited performance of knowledge reasoning models. To address these challenges, a hybrid knowledge graph method was adopted in the construction of a driving scenario knowledge graph (DSKG). Firstly, core concepts in the field were systematically sorted and classified, laying the foundation for the construction of a multi-level classified knowledge graph top-level ontology. Subsequently, by deeply exploring and analyzing the Traffic Genome data, 34 entities and 51 relations were extracted and integrated with the ontology layer, achieving the expansion and updating of the knowledge graph. Then, in terms of knowledge reasoning models, an analysis of the training results of the TransE, Complex, Distmult, and Rotate models in the entity linking prediction task of DSKG revealed that the Distmult model performed the best in metrics such as hit rate, making it more suitable for inference in DSKG. Finally, a standardized and widely applicable driving scenario knowledge graph was proposed. The DSKG and related materials have been publicly released for use by industry and academia.

A Graph-Based Keyword Extraction Method for Academic Literature Knowledge Graph Construction

In this paper, we construct an academic literature knowledge graph based on the relationship between documents to facilitate the storage and research of academic literature data. Keywords are an important type of node in the knowledge graph. To solve the problem that there are no keywords in some documents for several reasons in the process of knowledge graph construction, an improved keyword extraction algorithm called TP-CoGlo-TextRank is proposed by using word frequency, position, word co-occurrence frequency, and a word embedding model. By combining the word frequency and position in the document, the importance of words is distinguished. By introducing the GloVe word-embedding model, which brings the external knowledge of documents into the TextRank algorithm, and combining the internal word co-occurrence frequency in the documents, the word-adjacency relationship is transferred non-uniformly. Finally, the words with the highest scores are combined into phrases if they are adjacent in the original text. The validity of the TP-CoGlo-TextRank algorithm is verified by experiments. On this basis, the Neo4j graph database is used to store and display the academic literature knowledge graph, to provide data support for research tasks such as text clustering, automatic summarization, and question-answering systems.

Ontology-Driven Architecture for Managing Environmental, Social, and Governance Metrics

The burgeoning significance of environmental, social, and governance (ESG) metrics in realms such as investment decision making, corporate reporting, and risk management underscores the imperative for a robust, comprehensive solution capable of effectively capturing, representing, and analysing the multifaceted and intricate ESG data landscape. Facing the challenge of aligning with diverse standards and utilising complex datasets, organisations require robust systems for the integration of ESG metrics with traditional financial reporting. Amidst this, the evolving regulatory landscape and the demand for transparency and stakeholder engagement present significant challenges, given the lack of standardized ESG metrics in certain areas. Recently, the use of ontology-driven architectures has gained attention for their ability to encapsulate domain knowledge and facilitate integration with decision-support systems. This paper proposes a knowledge graph in the ESG metric domain to assist corporations in cataloguing and navigating ESG reporting requirements, standards, and associated data. Employing a design science methodology, we developed an ontology that serves as both a conceptual foundation and a semantic layer, fostering the creation of an interoperable ESG Metrics Knowledge Graph (ESGMKG) and its integration within operational layers. This ontology-driven approach promises seamless integration with diverse ESG data sources and reporting frameworks, while addressing the critical challenges of metric selection, alignment, and data verification, supporting the dynamic nature of ESG metrics. The utility and effectiveness of the proposed ontology were demonstrated through a case study centred on the International Financial Reporting Standards (IFRS) framework that is widely used within the banking industry.

Bibliometric Analysis of Research Progress and Trends on Carbon Emission Responsibility Accounting

The severity of global climate change is a pressing issue, and carbon emission reduction requires collaboration between producers and consumers. Carbon emission responsibility accounting is critical for distributing the tasks associated with carbon reduction. To examine the current research status and future development trends of carbon emission responsibility accounting, we used the scientific quantitative knowledge graph method and CiteSpace software. We analyzed the data from 4089 studies retrieved from the Web of Science and China National Knowledge Infrastructure databases, focusing on various aspects such as the number of published papers, subjects, research focuses, research content, and future research directions. In 2022, the number of publications was 657. The largest number of published carbon emission responsibility accounting documents was published by scholars from China: there were 708 published articles, 35% of the 2002 articles published in the Web of Science. The reason may be that China, as a developing country, produces more carbon emissions. In order to actively shoulder international responsibilities and slow down global warming, China strengthened its research on carbon emission responsibility, the basic work on carbon emission reduction. This was followed by the United States and England. England showed high levels of research collaboration. “Environmental science” was one of the main subjects in the Web of Science database, representing 43.96% of total publications. Research focuses included input–output analyses and implied carbon export trade. This study summarizes the literature on carbon emission responsibility accounting in terms of research perspectives, accounting principles, and accounting methods. In the future, the accounting of carbon emission responsibility at the city level considering the carbon emission responsibility sharing method including three or more shared parties and accounting for the carbon emission responsibility between the upstream and downstream from the perspective of the industrial chain can be studied. The findings of this study provide guidance to researchers and policymakers for the progression and enhancement of carbon emission responsibility accounting.