Knowledge Graph Research Articles

Who is Doing Taxonomy, Whereabouts, and Who Is Funding Them? A Practical Test of What Knowledge Graphs Can Tell Us about Taxonomic Research

Who is Doing Taxonomy, Whereabouts, and Who Is Funding Them? A Practical Test of What Knowledge Graphs Can Tell Us about Taxonomic Research

Uncovering emerging technologies in intelligent manufacturing via graph classification of community characteristics

Advancing the identification of emerging technology trends is pivotal for informed design decisions and risk mitigation. Our research introduces a novel methodology, centered on technology subgraphs within a patent knowledge graph, utilising graph neural networks combined with data augmentation techniques. This approach deviates from traditional methods, which primarily focus on individual patent nodes or the entire patent network. Instead, it segments the patent knowledge graph into subgraphs, analyzing them based on structural features to identify emerging technologies. Our method is further strengthened by employing an expert-curated emerging technology tag library, enabling a quantitative, rather than solely qualitative, assessment of the subgraphs’ relevance to emerging technologies. Additionally, we integrate comparative learning to enhance subgraph data quality, thereby boosting the reliability and accuracy of our approach. The results demonstrate a significant improvement in the accurate identification of emerging technologies, underscoring the effectiveness of our proposed model.

Integrating AI with medical industry chain data: enhancing clinical nutrition research through semantic knowledge graphs

In clinical nutrition research, the medical industry chain generates a wealth of multidimensional spatial data across various formats, including text, images, and semi-structured tables. This data’s inherent heterogeneity and diversity present significant challenges for processing and mining, which are further compounded by the data’s diverse features, which are difficult to extract. To address these challenges, we propose an innovative integration of artificial intelligence (AI) with the medical industry chain data, focusing on constructing semantic knowledge graphs and extracting core features. These knowledge graphs are pivotal for efficiently acquiring insights from the vast and granular big data within the medical industry chain. Our study introduces the Clinical Feature Extraction Knowledge Mapping (CFEKM) model, designed to augment the attributes of medical industry chain knowledge graphs through an entity extraction method grounded in syntactic dependency rules. The CFEKM model is applied to real and large-scale datasets within the medical industry chain, demonstrating robust performance in relation extraction, data complementation, and feature extraction. It achieves superior results to several competitive baseline methods, highlighting its effectiveness in handling medical industry chain data complexities. By representing compact semantic knowledge in a structured knowledge graph, our model identifies knowledge gaps and enhances the decision-making process in clinical nutrition research.

A data-driven method combining knowledge graph with deep learning for constructing machining process knowledge base

A data-driven method combining knowledge graph with deep learning for constructing machining process knowledge base

HGCGE: hyperbolic graph convolutional networks-based knowledge graph embedding for link prediction

HGCGE: hyperbolic graph convolutional networks-based knowledge graph embedding for link prediction

Towards trustworthy AI for link prediction in supply chain knowledge graph: a neurosymbolic reasoning approach

Modern supply chains are complex and interlinked, resulting in increased network risk exposure for companies. Digital Supply Chain Surveillance (DSCS) has emerged as a practice to proactively monitor these risks. Within DSCS, link prediction, a particular task whose objective is to identify hidden relationships in the supply chain, has been increasingly studied in the literature. While many approaches have been proposed, machine learning (ML) based techniques have recently gained wider attention due to their state-of-the-art performance across different benchmark datasets. However, adoption of these technologies in practice remains difficult. Their black-box nature have resulted in a lack of trustworthiness among practitioners. In this paper, we design a trustworthy ML approach based on recent theoretical development in neurosymbolic AI methods that enables a more transparent learning and reasoning process. We find that our approach is not only on par with state-of-the-art black box models when tested in two benchmark datasets on the automotive and energy industry but also addresses research gaps on explainability and complexity analysis.

SKH-NLP at LLMs4OL 2024 Task B: Taxonomy Discovery in Ontologies Using BERT and LLaMA 3

Taxonomy discovery in ontologies refers to extracting the parent class from the child class. By modeling this task as a classification problem, we addressed it using two different approaches. The first approach involved fine-tuning the “BERT-Large” model with various prompts and using it in a classification system. In the second approach, we utilized the “LLaMA 3 70B” model, experimenting with different prompts and modifying them to achieve the best results. Additionally, we evaluated the correctness of the answers using substring and Levenshtein distance functions. The results indicate that, with appropriate fine-tuning, the BERT model can achieve performance levels comparable to those of more recent and significantly larger language models, such as LLaMA 3 70B. However, with appropriate prompts, LLaMA 3 70B performs slightly better than BERT, highlighting the importance of prompt quality. Ultimately, further experiments on different settings for fine-tuning BERT, few-shot learning, and using knowledge graphs for validating the model's answers for LLaMA are recommended to improve the results. Additionally, testing other models and examining the results of various encoder-based and decoder-based models can be employed.

A Brief Survey on Deep Learning-Based Temporal Knowledge Graph Completion

Temporal knowledge graph completion (TKGC) is the task of inferring missing facts based on existing ones in a temporal knowledge graph. In recent years, various TKGC methods have emerged, among which deep learning-based methods have achieved state-of-the-art performance. In order to understand the current research status of TKGC methods based on deep learning and promote further development in this field, in this paper, for the first time, we summarize the deep learning-based methods in TKGC research. First, we detail the background of TKGC, including task definition, benchmark datasets, and evaluation protocol. Then, we divide the existing deep learning-based TKGC methods into eight fine-grained categories according to their core technology and summarize them. Finally, we conclude the paper and present three future research directions for TKGC.

Relation semantic fusion in subgraph for inductive link prediction in knowledge graphs

Inductive link prediction (ILP) in knowledge graphs (KGs) aims to predict missing links between entities that were not seen during the training phase. Recent some subgraph-based methods have shown some advancements, but they all overlook the relational semantics between entities during subgraph extraction. To overcome this limitation, we introduce a novel inductive link prediction model named SASILP (Structure and Semantic Inductive Link Prediction), which comprehensively incorporates relational semantics in both subgraph extraction and node initialization processes. The model employs a random walk strategy to calculate the structural scores of neighboring nodes and utilizes an enhanced graph attention network to determine their semantic scores. By integrating both structural and semantic scores, SASILP strategically selects key nodes to form a subgraph. Furthermore, the subgraph is initialized with a node initialization technique that integrates information about neighboring relations. The experiments conducted on benchmark datasets demonstrate that SASILP outperforms state-of-the-art methods on inductive link prediction tasks, and verify the effectiveness of our approach.

A knowledge graph-enabled multi-domain mapping approach supporting product rapid design: A case study of new energy vehicles

In the context of mass personalization, the dynamic and erratic nature of customer requirements (CRs) is increasingly pronounced. Amidst intensifying market competition, enterprises are compelled to swiftly adjust their products to satisfy the ever-changing CRs. However, the complicated design processes often result in prolonged product update and iteration cycles. Thus, it is urgent for enterprises to promote product rapid design, in which, it is essential to map CRs to functional requirements (FRs), then to design parameters (DPs). Traditional mapping methods are time-consuming and labor-intensive, struggle to keep pace with the ever-changing CRs. Moreover, enhancing the efficiency of design knowledge management and reuse is imperative for achieving product rapid design. Considering the strengths of knowledge graphs (KGs) in knowledge management and mining, we establish a multi-domain product design KG (MPDKG) including a CR domain, a FR domain, and a DP domain, and facilitate the mapping process by constructing mapping relations between domains. Firstly, CR entities in the CR domain are extracted through a triple-task cascaded CRs identification model from online reviews and complaints. Secondly, FR entities are identified from product functional lists and instructions, and the Sentence-Bert model is employed to establish the mapping relations between CR entities and FR entities. Subsequently, a corpus comprising product design knowledge is constructed and a cross-domain joint entity relation extraction model is developed to extract DP entities and construct their mapping relations with FR entities. Lastly, the multi-domain mapping of BYD Qin is implemented as a case study to elucidate the practical utility and effectiveness of the proposed methodology.

The PrescIT platform: An interoperable Clinical Decision Support System for ePrescription to Prevent Adverse Drug Reactions and Drug-Drug Interactions.

Preventable medication errors have been proven to cause significant public health burden, and ePrescription is a key part of the process where medication errors and adverse effects could be prevented. Information systems and "intelligent" computational approaches could provide a valuable tool to prevent such errors with profound impact in clinical practice. The PrescIT platform is a Clinical Decision Support System (CDSS) that aims to facilitate the prevention of adverse drug reactions (ADRs) and drug-drug interactions (DDIs) in the phase of ePrescription in Greece. The proposed platform could be relatively easily localized for use in other contexts too. The PrescIT platform is based on the use of Knowledge Engineering (ΚΕ) approaches, i.e., the use of Ontologies and Knowledge Graphs (KGs) developed upon openly available data sources. Open standards (i.e., RDF, OWL, SPARQL) are used for the development of the platform enabling the integration with already existing IT systems or for standalone use. The main KG is based on the use of DrugBank, MedDRA, SemMedDB and OpenPVSignal. In addition, the Business Process Management Notation (BPMN) has been used to model long-term therapeutic protocols used during the ePrescription process. Finally, the produced software has been pilot tested in three hospitals by 18 clinical professionals via in-person think-aloud sessions. The PrescIT platform has been successfully integrated in a transparent fashion in a proprietary Hospital Information System (HIS), and it has also been used as a standalone application. Furthermore, it has been successfully integrated with the Greek National ePrescription system. During the pilot phase, one psychiatric therapeutic protocol was used as a testbed to collect end-users' feedback. Summarizing the feedback from the end-users, they have generally acknowledged the usefulness of such a system while also identifying some challenges in terms of usability and the overall user experience. The PrescIT platform has been successfully deployed and piloted in real-world environments to evaluate its ability to support safer medication prescriptions.

Federating cross-domain BIM-based knowledge graph

Despite decades of the digitization of the construction industry, interoperability challenges prevail. One of which is the lack of sufficient integration between domain-specific BIM models. Therefore, the paper proposes a novel methodology for federating cross-domain BIM-based knowledge graphs. The approach leverages the integration of multiple models into a single knowledge graph, aiming to bridge the existing gaps in data exchange and enhance the semantic richness of building information models. Through a detailed exploration of existing data exchange mechanisms, popular ontologies, and schema limitations, this research addresses the interoperability dilemma. A practical demonstration, encapsulated in the “LBD-Online-Merge” demo application, validates the methodology’s efficacy in real-world scenarios, illustrating its potential to revolutionize building operations management and data preparation for the operational phase of a building’s lifecycle. This study significantly contributes to the academic and practical discourse by providing a robust framework for achieving a more integrated, intelligent building information management ecosystem, setting a new benchmark for future research and applications in constructing semantically rich digital twins of the built environment.

A platform-based Natural Language processing-driven strategy for digitalising regulatory compliance processes for the built environment

The digitalisation of the regulatory compliance process has been an active area of research for several decades. However, more recently the level of activities in this area has increased considerably. In the UK, the tragic incident of Grenfell fire in 2017 has been a major catalyst for this as a result of the Hackitt report’s recommendations pointing a lot of the blame on the broken regulatory regime in the country. The Hackitt report emphasises the need to overhaul the building regulations, but the approach to do so remains an open research question. Existing work in this space tends to overlook the processing of actual regulatory documents, or limits their scope to solving a relatively small subtask. This paper presents a new comprehensive platform approach to the digitalisation of the regulatory compliance processing. We present i-ReC (intelligent Regulatory Compliance), a platform approach to digitalisation of regulatory compliance that takes into consideration the enormous diversity of all the stakeholders’ activities. A historical perspective on research in this area is first presented to put things in perspective which identifies the challenges in such an endeavour and identifies the gaps in state-of-the-art. After enumerating all the challenges in implementing a platform-based approach to digitalising the regulatory compliance process, the implementation of some parts of the platform is described. Our research demonstrates that the identification and extraction of all relevant requirements from the corpus of several hundred regulatory documents is a key part of the whole process which underlies the entire process from authoring to eventually compliance checking of designs. Some of the issues that need addressing in this endeavour include ambiguous language, inconsistent use of terms, contradicting requirements and handling multi-word expressions. The implementation of these tools is driven by NLP, ML and Semantic Web technologies. A semantic search engine was developed and validated against other popular and comparable engines with a corpus of 420 (out of about 800) documents used in the UK for compliance checking of building designs. In every search scenario, our search engine performed better on all objective criteria. Limitations of the approach are discussed which includes the challenges around licensing for all the documents in the corpus. Further work includes improving the performance of SPaR.txt (the tool created to identify multi-word expressions) as well as the information retrieval engine by increasing the dataset and providing the model with examples from more diverse formats of regulations. There is also a need to develop and align strategies to collect a comprehensive set of domain vocabularies to be combined in a Knowledge Graph.

A self-supervised entity alignment framework via attribute correction

Entity alignment (EA), aiming to match entities with the same meaning across different knowledge graphs (KGs), is a critical step in knowledge fusion. Existing EA methods usually encode the multi-aspect features of entities as embeddings and learn to align the embeddings with supervised learning. Although these methods have achieved remarkable results, two issues have not been well addressed. Firstly, these methods require pre-aligned entity pairs to perform EA tasks, limiting their applicability in practice. Secondly, these methods overlook the unique contribution of digital attributes to EA tasks when utilising attribute information to enhance entity features. In this paper, we propose a self-supervised entity alignment framework via attribute correction. Specifically, we first design a highly effective seed pair generator based on multi-aspect features of entities to solve the labor-intensive problem of obtaining pre-aligned entity pairs. Then, a novel alignment mechanism via attribute correction is proposed to address the problem that different types of attributes have different contributions to the EA task. Extensive experiments on real-world datasets with semantic features demonstrate that our framework outperforms state-of-the-art (SOTA) EA tasks.

Revealing the coupled evolution process of construction risks in mega hydropower engineering through textual semantics

Mega hydropower engineering (MHE) involves complex construction processes, harsh environments, and highly mobile personnel, equipment, and other resources, resulting in a high incidence of construction risks and significant difficulties in safety control. Previous studies extensively explored the identification and governance of risks in MHE. However, these studies did not adequately utilize accident report case texts, and the coupled evolutionary law of construction risks remains unclear. To address this gap, this study developed a Bert-based Global Pointer Network for Named Entity-Relation Joint Extraction (Bert-GPLinker) to extract risk factors and their relationships. Second, the extracted risk factors and their relationships were employed to construct a knowledge graph, integrating text matching and path inference algorithms to propose a coupled evolutionary path reasoning method for construction risks. Finally, the coupled interactions among the risk factors were considered, and the interaction matrix principle was utilized to quantitatively assess the importance of each risk factor in the knowledge graph. The results showed that (1) the F1 value of Bert-GPLinker on the self-built dataset was 91.90%, indicating better model performance; (2) the coupled evolutionary reasoning system can quickly deduce the evolutionary path with the highest probability of any risk node and the types of accidents that may result; and (3) among the top 25 risk factors in terms of importance, those in the management system category accounted for 52%, with higher importance mainly concentrated in inspection, supervision, and training.

Developments of AI Systems using Knowledge Graphs and Ontologies

Developments of AI Systems using Knowledge Graphs and Ontologies

Knowledge Representation Learning Method Based on Semantic Enhancement of External Information

Background: Knowledge representation learning aims at mapping entity and relational data in knowledge graphs to a low-dimensional space in the form of vectors. The existing work has mainly focused on structured information representation of triples or introducing only one additional kind of information, which has large limitations and reduces the representation efficiency. Objective: This study aims to combine entity description information and textual relationship description information with triadic structure information, and then use the linear mapping method to linearly transform the structure vector and text vector to obtain the joint representation vector. Methods: A knowledge representation learning (DRKRL) model that fuses external information for semantic enhancement is proposed, which combines entity descriptions and textual relations with a triadic structure. For entity descriptions, a vector representation is performed using a bi-directional long- and short-term memory network (Bi-LSTM) model and an attention mechanism. For the textual relations, a convolutional neural network is used to vectorially encode the relations between entities, and then an attention mechanism is used to obtain valuable information as complementary information to the triad. Results: Link prediction and triadic group classification experiments were conducted on the FB15K, FB15K-237, WN18, WN18RR, and NELL-995 datasets. Theoretical analysis and experimental results show that the DRKRL model proposed in this paper has higher accuracy and efficiency compared with existing models. Conclusion: Combining entity description information and textual relationship description information with triadic structure information can make the model have better performance and effectively improve the knowledge representation learning ability.

A Dynamic Sandbox Detection Technique in a Private Cloud Environment

In specific private cloud scenarios, how to defend against malicious software and ensure data security is one of the current research hotspots, and sandbox is an important detection method. This paper proposes a dynamic behavior detection technique based on sandboxing, which real-time monitors and analyzes malicious software behavior. By improving the sandbox behavior weight, integrating virtual resources, and designing fine-grained access control, the detection accuracy and efficiency are enhanced based on zero trust access control system. The simulated attacks are identified on the testing platform, drawing knowledge graphs, achieving effective discovery and tracing. Meanwhile, this paper verified through experiments that the system consumption of the detection method is within an acceptable range, expanding the detection range and reducing the missed detection rate.

CVD Atlas: a multi-omics database of cardiovascular disease.

Cardiovascular disease (CVD) is the leading cause of illness and death worldwide. Numerous studies have been conducted into the underlying mechanisms and molecular characteristics of CVD using various omics approaches. However, there is still a need for comprehensive resources on CVD. To fill this gap, we present the CVD Atlas, accessed at https://ngdc.cncb.ac.cn/cvd. This database compiles knowledge and information from manual curation, large-scale data analysis, and existing databases, utilizing multi-omics data to understand CVDs comprehensively. The current version of CVD Atlas contains 215,333 associations gathered from 308 publications, 652 datasetsand 7 databases. It covers 190 diseases and 44 traits across multiple omics levels. Additionally, it provides an interactive knowledge graph that integrates disease-gene associations and two types of analysis tools, offering an engaging way to query and display relationships. CVD Atlas also features a user-friendly web interface that allows users to easily browse, search, and download all association information, research metadata, and annotation details. In conclusion, CVD Atlas is a valuable resource that enhances the accessibility and utility of knowledge and information related to CVD, benefiting human health and CVD research communities.

The joint extraction of fact-condition statement and super relation in scientific text with table filling method

The fact-condition statements are of great significance in scientific text, via which the natural phenomenon and its precondition are detailly recorded. In previous study, the extraction of fact-condition statement and their relation (super relation) from scientific text is designed as a pipeline that the fact-condition statement and super relation are extracted successively, which leads to the error propagation and lowers the accuracy. To solve this problem, the table filling method is firstly adopted for joint extraction of fact-condition statement and super relation, and the Biaffine Convolution Neural Network model (BCNN) is proposed to complete the task. In the BCNN, the pretrained language model and Biaffine Neural Network work as the encoder, while the Convolution Neural Network is added into the model as the decoder that enhances the local semantic information. Benefiting from the local semantic enhancement, the BCNN achieves the best F1 score with different pretrained language models in comparison with other baselines. Its F1 scores in GeothCF (geological text) reach 73.17% and 71.04% with BERT and SciBERT as pretrained language model, respectively. Moreover, the local semantic enhancement also increases its training efficiency, via which the tags’ distribution can be more easily learned by the model. Besides, the BCNN trained with GeothCF also exhibits the best performance in BioCF (biomedical text), which indicates that it can be widely applied for the information extraction in all scientific domains. Finally, the geological fact-condition knowledge graph is built with BCNN, showing a new pipeline for construction of scientific fact-condition knowledge graph.