Search

Driven by economic globalisation, various industries have developed a trend towards high specialisation and vertical division of labor, resulting in vast and intricate supply chain networks. However, unforeseen disasters can cause supply chain disruptions, subsequently impacting the regular production and operations of both upstream and downstream enterprises. To tackle this challenge, this study utilises Graph Neural Networks (GNNs) to synthesise graph structural data within the supply chain network, aiming to identify alternative suppliers to mitigate the impact of disruptions. We construct a large-scale knowledge graph to represent the realistic automotive supply chain network in China. Additionally, we propose a GNN-based framework that utilises information about interactions between buyers and suppliers to recommend alternative suppliers from the knowledge graph. Experimental results show that our approach significantly outperforms state-of-the-art GNN-based models, including Light-GCN and NGCF. Our research provides an intelligent and efficient perspective on supplier selection for the Chinese automobile industry. [ABSTRACT FROM AUTHOR]

The deployment of the Industrial Internet of Things (IIoT) in smart container terminals provides a foundation for sensing and recording all operational processes. However, little effort has been devoted to integrating the massive data regarding interoperability challenges, thus limiting the value of data in advancing the intelligent evolution of ports. In this research, we propose a graph-based approach to organise operational records semantically, thereby facilitating data-driven decision-making in container terminals. We first construct a knowledge graph for operational processes in container terminals, employing a tailored procedure for the automatic conversion of operational records into triples. By utilising the graph information, we propose a novel method that integrates reinforcement learning (RL) with a mathematical solver for optimising scheduling problems. The quay crane scheduling problem (QCSP) is illustrated as an example to elaborate on the technical details. Based on a dataset from a real-world container terminal, numerical studies demonstrate the superiority of the proposed framework in terms of information retrieval efficiency and solution quality compared with the traditional data organisation approach. [ABSTRACT FROM AUTHOR]

Modern supply chains are complex, interconnected systems that contain emergent, invisible dependencies. Lack of visibility often hinders effective risk planning and results in delayed discovery of supply chain problems, with examples ranging from product contamination, unsustainable production practices, or exposure to suppliers clustered in geographical areas prone to natural or man-made disasters. Initiatives that rely on manual collection of data often fail due to supply chain complexity and unwillingness of suppliers to share data. In this paper, we propose a neurosymbolic machine learning technique to proactively uncover hidden risks in supply chains and discover new information. Our method uses a combination of graph neural networks and knowledge graph reasoning. Unlike existing research our model is able to infer multiple types of hidden relationship risks, presenting a step change in automated supply chain surveillance. The approach has been tested on two empirical datasets from the automotive and energy industries, illustrating that it can provide inference in multiple types of links such as companies, products, production capabilities, certifications; thereby facilitating complex queries that go beyond who-supplies-whom. As such, additional risk insights can emerge from graph structure, providing practitioners with new knowledge. [ABSTRACT FROM AUTHOR]

Micro, Small, and Medium-sized Enterprises (MSMEs) are essential for the growth and development of the country's economy, as they create jobs, generate income, and foster production and innovation. In recent years, credit risk assessment (CRA) has been an essential process used by financial institutions to evaluate the creditworthiness of MSMEs and determine the likelihood of default. Traditionally, CRA has relied on credit scores and financial statements, but with the advent of machine learning (ML) algorithms, lenders have a new tool at their disposal. By and large, ML algorithms are designed to classify borrowers based on their credit history and transactional data while leveraging the entity relationship involved in credit transactions. This study introduces an innovative knowledge graph-driven credit risk assessment model (RGCN-RF) based on the Relational Graph Convolutional Network (RGCN) and Random Forest (RF) algorithm. RGCN is employed to identify topological structures and relationships, which is currently nascent in traditional credit risk assessment methods. RF categorises MSMEs based on the enterprise embedding vector generated from RGCN. Extensive experimentation is conducted to assess model performance utilising the Indian MSMEs database. The balanced accuracy of 92% obtained using the RGCN-RF model demonstrates a considerable advancement over prior techniques in identifying risk-free enterprises. [ABSTRACT FROM AUTHOR]

Despite tremendous recent progress, extant artificial intelligence (AI) still falls short of matching human learning in effectiveness and efficiency. One fundamental disparity is that humans possess a wealth of prior knowledge, while AI lacks the essential commonsense knowledge required for learning tasks. Guided by schema theory, we employ the design science research methodology to introduce a novel knowledge-aware learning framework to harness the knowledge-based processes in human learning. Unlike existing pre-trained large language models (LLMs) and knowledge-aware approaches that treat knowledge in considerably different ways from humans, our theoretically grounded framework closely mimics how humans acquire, represent, activate, and utilize knowledge. The extensive evaluations in the context of text analytics tasks demonstrate that our design achieves comparable performance to the state-of-the-art LLMs and enhances model generalizability and learning efficiency. This study takes a step forward by bringing cognitive science into building cognitively plausible AI and human-AI collaboration research. [ABSTRACT FROM AUTHOR]

BACKGROUND: Scoliosis mainly refers to sequence abnormalities in the coronal, sagittal, and axial positions of the spine, with a Cobb angle of ≥ 10°. The patients may experience symptoms such as unequal shoulder height and back asymmetry. Severe cases may affect the patient’s cardiopulmonary function, thereby affecting their daily life. Conservative treatment can control the progression of scoliosis and avoid later surgery. Scoliosis orthosis is currently a commonly used and effective treatment measure in conservative treatment. OBJECTIVE: To summarize and analyze the current research status, hotspots, and trends of scoliosis orthoses both domestically and internationally, providing reference for related research. METHODS: Using bibliometrics and visual analysis as tools, and using a comparison between China and foreign countries as a method, this paper analyzes the literature on scoliosis orthosis journals in the past decade. Based on bibliometrics, the current status of research on scoliosis orthoses is determined. Citespace software is used to analyze key words and identify the current hotspots and future trends in scoliosis orthosis research. RESULTS AND CONCLUSION: (1) At present, the number of literature on scoliosis orthoses is still on a fluctuating upward trend. China and the United States are the main countries for research, with a literature share of over 40%. However, the average citation rate of foreign language literature by Chinese scholars is relatively low. (2) The basic fields of domestic research are mainly surgery and pediatrics, while orthotics and clinical neurology are mainly studied abroad. Among them, there is also a certain number of documents in domestic Chinese medicine, indicating that China is also engaged in the combination of Chinese and Western treatment of scoliosis. The National Natural Science Foundation of China has the highest proportion in the aspect of Chinese and foreign literature, reflecting the importance of the fund attaches to the research of scoliosis orthosis. (3) The authors with the highest number of publications are Qiu Yong and Negrini Stefano, and the most published institutions are the Spinal Surgery Department of Gulou Hospital affiliated to Nanjing University Medical College and UDICE-French Research University. Domestic and foreign authors and institutions have certain communications about this, but not closely, which requires relevant institutions and scholars to further explore and study. (4) From the research hotspots and future trends, the main treatment type is adolescent idiopathic scoliosis, while the production method of the short-column side bending orthosis is three-dimensinoal printing, and the main treatment index is convex progression. The ultimate purpose of treatment is to improve the quality of life of the patients. [ABSTRACT FROM AUTHOR]

Background: Target identification and hit identification can be transformed through the application of biomedical knowledge analysis, AI-driven virtual screening and robotic cloud lab systems. However there are few prospective studies that evaluate the efficacy of such integrated approaches. Results: We synergistically integrate our in-house-developed target evaluation (SpectraView) and deep-learning-driven virtual screening (HydraScreen) tools with an automated robotic cloud lab designed explicitly for ultra-high-throughput screening, enabling us to validate these platforms experimentally. By employing our target evaluation tool to select IRAK1 as the focal point of our investigation, we prospectively validate our structure-based deep learning model. We can identify 23.8% of all IRAK1 hits within the top 1% of ranked compounds. The model outperforms traditional virtual screening techniques and offers advanced features such as ligand pose confidence scoring. Simultaneously, we identify three potent (nanomolar) scaffolds from our compound library, 2 of which represent novel candidates for IRAK1 and hold promise for future development. Conclusion: This study provides compelling evidence for SpectraView and HydraScreen to provide a significant acceleration in the processes of target identification and hit discovery. By leveraging Ro5's HydraScreen and Strateos' automated labs in hit identification for IRAK1, we show how AI-driven virtual screening with HydraScreen could offer high hit discovery rates and reduce experimental costs. Scientific contribution: We present an innovative platform that leverages Knowledge graph-based biomedical data analytics and AI-driven virtual screening integrated with robotic cloud labs. Through an unbiased, prospective evaluation we show the reliability and robustness of HydraScreen in virtual and high-throughput screening for hit identification in IRAK1. Our platforms and innovative tools can expedite the early stages of drug discovery. [ABSTRACT FROM AUTHOR]

Research suggests that individuals who experience prolonged exposure to stress may be at higher risk for developing psychological stress disorders. Currently, psychological stress is primarily evaluated by professional physicians using rating scales, which may be prone to subjective biases and limitations of the scales. Therefore, it is imperative to explore more objective, accurate, and efficient biomarkers for evaluating the level of psychological stress in an individual. In this study, we utilized 4D data-independent acquisition (4D-DIA) proteomics for quantitative protein analysis, and then employed support vector machine (SVM) combined with SHAP interpretation algorithm to identify potential biomarkers for psychological stress levels. Biomarkers validation was subsequently achieved through machine learning classification and a substantial amount of a priori knowledge derived from the knowledge graph. We performed cross-validation of the biomarkers using two batches of data, and the results showed that the combination of Glyceraldehyde-3-phosphate dehydrogenase and Fibronectin yielded an average area under the curve (AUC) of 92%, an average accuracy of 86%, an average F1 score of 79%, and an average sensitivity of 83%. Therefore, this combination may represent a potential approach for detecting stress levels to prevent psychological stress disorders. [ABSTRACT FROM AUTHOR]

Entity alignment (EA) aims to discover the equivalent entities in different knowledge graphs (KGs), which plays an important role in knowledge engineering. Recently, EA with dangling entities has been proposed as a more realistic setting, which assumes that not all entities have corresponding equivalent entities. In this paper, we focus on this setting. Some work has explored this problem by leveraging translation API, pre-trained word embeddings, and other off-the-shelf tools. However, these approaches over-rely on the side information (e.g., entity names) and fail to work when the side information is absent. On the contrary, they still insufficiently exploit the most fundamental graph structure information in KG. To improve the exploitation of the structural information, we propose a novel entity alignment framework called Structure-aware Wasserstein Graph Contrastive Learning (SWGCL), which is refined on three dimensions: (i) Model. We propose a novel Gated Graph Attention Network to capture local and global graph structure attention. (ii) Training. Two learning objectives: contrastive learning and optimal transport learning, are designed to obtain distinguishable entity representations. (iii) Inference. In the inference phase, a PageRank-based method HOSS (Higher-Order Structural Similarity) is proposed to calculate higher-order graph structural similarity. Extensive experiments on two dangling benchmarks demonstrate that our SWGCL outperforms the current state-of-the-art methods with pure structural information in both traditional (relaxed) and dangling (consolidated) settings. [ABSTRACT FROM AUTHOR]

Additive Manufacturing (AM) technology offers remarkable flexibility in fabricating products with intricate geometries, presenting unprecedented advantages in material efficiency and speed. The process planning of AM plays a pivotal role in ensuring overall quality and time-efficiency of printed products. This drives engineers and researchers to explore various approaches to achieve optimal AM process solutions. However, numerous challenges persist, particularly in logical relationship reasoning and information representation for complex manufacturing tasks and design requirements. In this study, a novel AM process reasoning method based on relation mining is proposed, leveraging knowledge graph representation and graph neural networks (GNN). An AM knowledge graph is constructed comprising essential process information, followed by implementing RED-GNN to accomplish graph reasoning tasks for parameter recommendation. We then focus on the process planning scenario of lattice structures, a common geometry used for designing products with weight-relief requirements and high sensitivity to process parameters. A series of lattice structure parts are designed and tested using our proposed method, demonstrating strong performance and unveiling new potentials and opportunities in advancing knowledge-based engineering and intelligent manufacturing. [ABSTRACT FROM AUTHOR]

The rapid advancement of artificial intelligence has significantly expanded the role of service robots in everyday life. This expansion necessitates the accurate recognition and prediction of human intentions to provide timely and appropriate services. However, existing methods often struggle to perform effectively in complex and unstructured environments. To address this challenge, we propose the Large language model and Knowledge graph based Intention Recognition Framework (LKIRF), which combines large language model (LLM) with knowledge graphs (KG) to enhance the intention recognition capabilities of service robots. Our approach constructs an offline KG from human motion and environmental data and builds an online reasoning graph through real-time interaction, utilizing LLM for interpretation. Experimental results indicate that compared to traditional methods, LKIRF not only improves prediction accuracy across various scenarios but also enhances the transparency and interpretability of the intention reasoning process. [ABSTRACT FROM AUTHOR]

The demand for functionality, performance, safety, and reliability in complex product domains is continuously increasing, leading to growing product complexity. Traditional document-based systems engineering approaches face numerous challenges in terms of communication efficiency, traceability, and maintenance when dealing with complex product system design. Consequently, Model-Based Systems Engineering (MBSE) has been widely adopted. To improve the efficiency of system modelling, an effective method is needed to automate the process by reusing existing design resources. This study proposes a knowledge graph-based approach for the automatic generation of system model diagrams, consisting of three main steps. Firstly, a system model graph is constructed using an existing system model repository. Then, the required modelling elements are extracted from design documents, and reusable model elements are obtained based on the system model graph. Lastly, a mapping relationship is established between system model elements extracted from multi-source heterogeneous data and SysML metamodel, enabling the automatic generation of system model diagrams based on SysML views. This approach effectively leverages the information from the existing system model repository and achieves automated mapping conversion from multi-source heterogeneous data to the SysML system model. A communication satellite case study is presented to demonstrate the capability of this method. [ABSTRACT FROM AUTHOR]

Owing to the rapid development of Earth observation and Internet technology, researchers have acquired and shared a large amount of Earth observation data. However, traditional data sharing does not provide direct solutions to problems. The large amount of tacit knowledge contained in scientific data, scientific literature, analysis models, software/code, documentation, and other scientific resources on Earth observation applications has not been effectively organized and shared. To solve this problem, the Group on Earth Observations proposed an Earth Observation Knowledge Hub (EOKH); however, there is no unified and clear method for building an EOKH to date. This paper presents an automatic construction method for an EOKH on the basis of a knowledge graph, which describes scientific data, scientific literature, analysis models, software/code, documentation, and other scientific resources and their semantic relationships. An automatic discovery algorithm of scientific and technological resources was also constructed in this study on the basis of a knowledge graph from the Internet. This algorithm is capable of the automatic creation of knowledge packages and the construction of links between knowledge elements. Then, the knowledge discovery algorithm was evaluated through comparison with an existing method in relation to accuracy, and the results showed that our method outperforms the existing method. Lastly, the knowledge package was published on the Linked Open Data Cloud platform in the Resource Description Framework format, and an EOKH was created. Moreover, an application terminal based on SPARQL allowing users to search the EOKH was developed. A clear and operational method for the construction of an EOKH is proposed for the first time in this research, laying the foundation for the development of the EOKH. [ABSTRACT FROM AUTHOR]

Objective To analyze the progress and current status of ethical research in the field of organ donation and transplantation in China by bibliometric analysis. Methods Literature review was conducted from CNKI between January 2000 to December 2023. The number of published articles, the cooperation network of core authors, the cooperation network of publication institutions, the co-occurrence of keywords, the emergent keywords and the clustering of keywords were analyzed by CiteSpace 6.2.6. Results A total of 399 valid articles were obtained. The three peaks in the trend of published articles were affected by current policy events and the development of transplantation technology. From 2000 to 2014, the number of published articles showed an upward trend. At this stage, these studies focused on ethical speculation in the field of organ donation and transplantation. From 2015 to 2023, the number of published articles showed a fluctuating trend. During this stage, these researches highlighted the work system of donation and transplantation and ethical issues in medical practice. Organ donation and ethical review after citizen death became the research frontiers. The co-occurrence knowledge map of authors reflected that the authors mainly served as single nodes, lacking of communication among authors. Twenty-five core authors were identified. Diverse publication institutions were searched including medical departments from colleges and universities, ethics research institutions, organ transplantation departments from hospitals, ethics committees from hospitals and human Organ Procurement Organization (OPO), etc. The First Hospital of Kunming published the largest number of articles. A total of 252 keywords and 13 emergent words were extracted. The keywords with the highest degree of emergency consisted of brain death, organ donation, legislation and ethical review. A total of 14 keyword clusters were generated, including organ transplantation, organ donation, organ donation after citizen’s death, ethics, ethical review and medical staff. Conclusions The cooperation among authors and institutions is insufficient in the field of organ donation and transplantation ethics. Multi-center research and cooperation among authors should be strengthened. Extensive efforts should be made to strengthen the exploration and empirical research of ethical issues based on current work system and medical practice, aiming to provide ethical basis and defense for the reform and practice of organ donation and transplantation. [ABSTRACT FROM AUTHOR]

The rapid growth of biomedical literature makes it challenging for researchers to stay current. Integrating knowledge from various sources is crucial for studying complex biological systems. Traditional text-mining methods often have limited accuracy because they don't capture semantic and contextual nuances. Deep-learning models can be computationally expensive and typically have low interpretability, though efforts in explainable AI aim to mitigate this. Furthermore, transformer-based models have a tendency to produce false or made-up information—a problem known as hallucination—which is especially prevalent in large language models (LLMs). This study proposes a hybrid approach combining text-mining techniques with graph neural networks (GNNs) and fine-tuned large language models (LLMs) to extend biomedical knowledge graphs and interpret predicted edges based on published literature. An LLM is used to validate predictions and provide explanations. Evaluated on a corpus of experimentally confirmed protein interactions, the approach achieved a Matthews correlation coefficient (MCC) of 0.772. Applied to insomnia, the approach identified 25 interactions between 32 human proteins absent in known knowledge bases, including regulatory interactions between MAOA and 5-HT2C, binding between ADAM22 and 14-3-3 proteins, which is implicated in neurological diseases, and a circadian regulatory loop involving RORB and NR1D1. The hybrid GNN-LLM method analyzes biomedical literature efficiency to uncover potential molecular interactions for complex disorders. It can accelerate therapeutic target discovery by focusing expert verification on the most relevant automatically extracted information. [ABSTRACT FROM AUTHOR]

Knowledge graphs have recently been introduced to the verification strategy field successfully representing the complexity of verification in real‐life applications. This format provides a scale‐free analysis of verification strategies compared to the more traditional verification artifacts such as requirement traceability matrices and verification matrices. Complexities can be observed visually and numerically both in terms of the problem scope and the entity interdependencies. In this paper, we retrieve verification strategy information patterns representing different aspects of verification. This is achieved by tapping into the network properties of knowledge graphs. They are dissected to detect knowledge patterns emerging from different parts of the verification artifacts. Similarities and differences between the two verification strategies are explained numerically and semantically. Seemingly unrelated requirements and verification activities are connected through indirect connections, and orthogonalities between independent requirements are analyzed. These findings validate the scalability of verification planning and assessment based on knowledge graphs. [ABSTRACT FROM AUTHOR]

Predicting drug-target interactions (DTI) is a crucial stage in drug discovery and development. Understanding the interaction between drugs and targets is essential for pinpointing the specific relationship between drug molecules and targets, akin to solving a link prediction problem using information technology. While knowledge graph (KG) and knowledge graph embedding (KGE) methods have been rapid advancements and demonstrated impressive performance in drug discovery, they often lack authenticity and accuracy in identifying DTI. This leads to increased misjudgment rates and reduced efficiency in drug development. To address these challenges, our focus lies in refining the accuracy of DTI prediction models through KGE, with a specific emphasis on causal intervention confidence measures (CI). These measures aim to assess triplet scores, enhancing the precision of the predictions. Comparative experiments conducted on three datasets and utilizing 9 KGE models reveal that our proposed confidence measure approach via causal intervention, significantly improves the accuracy of DTI link prediction compared to traditional approaches. Furthermore, our experimental analysis delves deeper into the embedding of intervention values, offering valuable insights for guiding the design and development of subsequent drug development experiments. As a result, our predicted outcomes serve as valuable guidance in the pursuit of more efficient drug development processes. • The confidence method based on causal intervention is applied to drug target link prediction. • Three data sets and nine KGE models were used to verify the robustness of the proposed method. • The robustness of the results was evaluated by the optimal score and the dimension of the intervention input vector. • A comprehensive introduction to the algorithm and extensive experiments are conducted. [ABSTRACT FROM AUTHOR]

The article introduces focuses on advancements in XLORE 3, a multilingual knowledge graph built to integrate and manage knowledge from diverse resources. Topics include the creation of an extensive XLORE ontology for managing entities across languages, the merging of equivalent entities for enhanced knowledge sharing, and a multi-strategy framework for knowledge completion using pre-trained language models.

Knowledge graph (KG) is a representative technique of knowledge engineering, and it is often used in various intelligence applications, which assume that all triples in knowledge graphs (KGs) are correct. However, due to the noise brought by automatic KG construction techniques and the fuzziness of knowledge in specific fields, measuring uncertainty of KGs (i.e., the confidence of each triple being true) is important to the tasks of error detection and fact verification. Existing studies on triple confidence measurement either only relies on explicit evidences or merely depends on embedding evidences, which causes the resulting confidences are not precise enough. To solve this problem, in this paper, we propose a new triple confidence measurement (TCM) method, which combines multiple heterogeneous evidences including explicit evidences (i.e., concept paths and neighbor concept subgraphs) and different embedding evidences acquired by large language model, KG embedding models, contrastive learning, and graph convolutional network. Experiments on different real-world datasets demonstrate not only the superiority of TCM in the tasks of error detection and link prediction, but also the effectiveness of all proposed explicit evidences and embedding evidences. [ABSTRACT FROM AUTHOR]

User–item bipartite graphs and knowledge graphs are frequently employed in recommender systems due to their ability to provide rich information for user and item modeling. However, existing recommender systems predominantly focus on modeling either the user or item individually, with few studies simultaneously considering both aspects. In this paper, we propose a novel double-ended recommendation model, DEKGCI, which aims to fully leverage the advantages of these two information sources. Specifically, DEKGCI harnesses the high-order connectivity information in the user–item bipartite graph to extract user representations, while utilizing the semantic information in the knowledge graph to enrich item representations. By doing so, DEKGCI concurrently learns both user and item representations, effectively capturing the intricate interaction information between users and items. The DEKGCI model was evaluated on three real-world datasets. Computational results demonstrate the high effectiveness of the proposed DEKGCI model compared to seven state-of-the-art reference methods from the literature. In particular, compared to the best-performing KFGAN model, DEKGCI achieved AUC gains of 0.335% in movie recommendations, and F1 gains of 0.023%, 2.203%, and 0.530% in movie, book, and music recommendations, respectively. The code and data are available at https://github.com/miaomiao924/DEKGCI. [ABSTRACT FROM AUTHOR]

As consumer electronics evolve towards greater intelligence, their automation and complexity also increase, making it difficult for users to diagnose faults when they occur. To address the problem where users, relying solely on their own knowledge, struggle to diagnose faults in consumer electronics promptly and accurately, we propose a multimodal knowledge graph-based text generation method. Our method begins by using deep learning models like the Residual Network (ResNet) and Bidirectional Encoder Representations from Transformers (BERT) to extract features from user-provided fault information, which can include images, text, audio, and even olfactory data. These multimodal features are then combined to form a comprehensive representation. The fused features are fed into a graph convolutional network (GCN) for fault inference, identifying potential fault nodes in the electronics. These fault nodes are subsequently fed into a pre-constructed knowledge graph to determine the final diagnosis. Finally, this information is processed through the Bias-term Fine-tuning (BitFit) enhanced Chinese Pre-trained Transformer (CPT) model, which generates the final fault diagnosis text for the user. The experimental results show that our proposed method achieves a 4.4% improvement over baseline methods, reaching a fault diagnosis accuracy of 98.4%. Our approach effectively leverages multimodal fault information, addressing the challenges users face in diagnosing faults through the integration of graph convolutional network and knowledge graph technologies. [ABSTRACT FROM AUTHOR]

The primary objective of an effective recommender system is to provide accurate, varied, and personalized recommendations that align with the user's cognitive intents. Given their ability to represent structural and semantic information effectively, knowledge graphs (KGs) are increasingly being utilized to capture auxiliary information for recommendation systems. This trend is supported by the recent advancements in graph neural network (GNN)-based models for KG-aware recommendations. However, these models often struggle with issues such as insufficient user-item interactions and the misalignment of user intent weights during information propagation. Additionally, they face a popularity bias, which is exacerbated by the disproportionate influence of a small number of highly active users and the limited auxiliary information about items. This bias significantly curtails the effectiveness of the recommendations. To address this issue, we propose a Knowledge-Enhanced User Cognitive Intent Network (KeCAIN), which incorporates item category information to capture user intents with information aggregation and eliminate popularity bias based on causal reasoning in recommendation systems. Experiments on three real-world datasets show that KeCAIN outperforms state-of-the-art baselines. [ABSTRACT FROM AUTHOR]

Recently, knowledge graphs (KGs) have been shown to benefit many machine learning applications in multiple domains (e.g. self-driving, agriculture, bio-medicine, recommender systems, etc.). However, KGs suffer from incompleteness, which motivates the task of KG completion which consists of inferring new (unobserved) links between existing entities based on observed links. This task is achieved using either a probabilistic, rule-based, or embedding-based approach. The latter has been shown to consistently outperform the former approaches. It however relies on negative sampling, which supposes that every observed link is "true" and that every unobserved link is "false". Negative sampling increases the computation complexity of the learning process and introduces noise in the learning. We propose NSF-KGE, a framework for KG embedding that does not require negative sampling, yet achieves performance comparable to that of the negative sampling-based approach. NSF-KGE employs objectives from the non-contrastive self-supervised literature to learn representations that are invariant to relation transformations (e.g. translation, scaling, rotation etc) while avoiding representation collapse. [ABSTRACT FROM AUTHOR]

Knowledge representation learning is to project entities and relations into low-dimensional vector spaces, and efficiently calculate entities, relations, and complex semantic associations between them. However, the translation models that fuse multi-source information fail to specially pay attention to the semantic information of important sentences in the textual descriptions of an entity, which lead to the low quality of embedded representation of textual descriptions, and fail to utilize the primary neighbor of the entity to further constrain the entity representation, resulting in the weak knowledge representation learning ability of the models. To address these issues, we propose a joint knowledge representation learning model of sentence vectors weighting and primary neighbor constraints called SW &NC-Joint. First, the weight distribution of the sentences is calculated according to the frequency of the neighbors in each sentence, and then the textual descriptions are represented by the sentence vectors weighting. Secondly, the concept of neighbor association degree is put forward, and the primary neighbor is filtered out for each entity according to the association degree. Finally, the weighted textual description information and triple structure information are jointly trained, the most crucial thing that the model is constrained by using the distance between the entity and its primary neighbor in the training process, so as to improve the representation learning ability of the model. The link prediction and triple classification experiments are carried out on FB15K and WN18 datasets. The experimental results demonstrate that our model significantly outperforms existing state-of-the-art text-enhanced knowledge representation learning model for link prediction and triple classification tasks. [ABSTRACT FROM AUTHOR]

In the field of recommendation algorithms, Knowledge Graphs are often utilized as supplementary information to enhance recommendation accuracy. However, while applying Knowledge Graphs enriches recommendation information, it also introduces potentially misleading effects due to Knowledge Graph noise. To address these challenges, we propose a method to achieve Knowledge Graph Noise Reduction and Knowledge Perception Enhancement through positive contrast learning. The method employs Fourier Transform, Inverse Transform, and Convolution Optimization Computation techniques to transform and analyze Knowledge Graph triplet information in the frequency domain. The process filters and reduces noise through Convolution Optimization Computation by integrating frequency domain feature information, eliminating misleading relational information that cannot effectively infer user preferences. Subsequently, Positive Contrastive Learning enhances the acquired ternary information and improves the applicability of the information to recognize user preference information accurately. The proposed method reduces noise and enhances knowledge perception, strengthens the application of strong relationships, reduces the impact of weak relationships, and improves recommendation accuracy by utilizing frequency-domain features. The KG-CFCL_RippleNet and KG-CFCL_MKR models validate the effectiveness of this optimization method, and significant improvements are achieved in the area of book, music, and movie recommendations compared to existing models. Experiments demonstrate the advantages of KG-CFCL in terms of noise reduction, Knowledge Perception Enhancement, and data optimization, improving the interpretability of the models. [ABSTRACT FROM AUTHOR]

Due to its ability to effectively address the cold start and sparsity problems in collaborative filtering, knowledge graph is commonly used as auxiliary information in recommendation systems. However, the existing recommendation algorithms based on knowledge graphs mainly focus on utilizing the connection structure to obtain user interests or item features, without emphasizing the simultaneous feature extraction on both the user and item sides. Therefore, the learned embeddings can not effectively represent the potential semantics of users and items. In this paper, we proposed KAT, a knowledge-aware attentive recommendation model integrating two-terminal neighbor features, which to extract fine-grained user and item features by alternating preference propagation and neighborhood information aggregation. The two modules automatically update and share entity embedding. Specifically, we introduce knowledge-aware attention mechanism to enhance the distinction of adjacent entities. Furthermore, we design a neighbor sampling mechanism to calculate the maximum node influence by extracting the largest connected subnet, which avoids the instability of the model performance caused by random sampling. We validate the effectiveness of KAT on four different datasets: movie, music, book, and grape (the latter is a dataset that we constructed through market research). Numerous experiments have demonstrated that KAT significantly outperforms several recent baselines, and AUC and ACC have increased by 2.81% and 1.28% respectively on our self-built dataset. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Computer Engineering & Applications is the property of Beijing Journal of Computer Engineering & Applications Journal Co Ltd. and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

The advent of the Internet has led to the emergence of multi-source heterogeneous knowledge graphs, which have become a crucial means of storing and disseminating knowledge. Node importance estimation is a technique that is employed extensively in a number of fields, including recommender systems, intelligent search and resource allocation. This study introduces a Multi-perspective attention mechanism Fusion Algorithm for the mapping of multi-perspective features of knowledge graphs to Node Importance Estimation (MFA-NIE). First, structural embedding features, relational predicate features, and attribute features (both textual and quantitative) are established for the nodes. Subsequently, an enhanced attention mechanism is employed to extract, compress, and fuse these features. The fused hidden layer vector is employed in the design of a key-based attention mechanism, which enables the propagation of messages from neighboring nodes to the source node. This process results in the iterative updating of the source node’s hidden features. Finally, TOPSIS centrality, based on the topology of the source node, is employed to dynamically adjust the mapping between the fused features and node importance. Experiments were conducted on real-world, large-scale, multi-source, heterogeneous knowledge graphs, comparing the MFA-NIE algorithm with traditional and advanced baseline algorithms, including PR, PPR, GENI, RGTN, CLINE, MCRL, and others. The results demonstrate that the MFA-NIE algorithm significantly improves effectiveness and accuracy, showcasing its superiority, versatility, and practical application value. [ABSTRACT FROM AUTHOR]

Drug resistance poses a crucial challenge in healthcare, with response rates to chemotherapy and targeted therapy remaining low. Individual patient's resistance is exacerbated by the intricate heterogeneity of tumor cells, presenting significant obstacles to effective treatment. To address this challenge, DrugFormer, a novel graph‐augmented large language model designed to predict drug resistance at single‐cell level is proposed. DrugFormer integrates both serialized gene tokens and gene‐based knowledge graphs for the accurate predictions of drug response. After training on comprehensive single‐cell data with drug response information, DrugFormer model presents outperformance, with higher F1, precision, and recall in predicting drug response. Based on the scRNA‐seq data from refractory multiple myeloma (MM) and acute myeloid leukemia (AML) patients, DrugFormer demonstrates high efficacy in identifying resistant cells and uncovering underlying molecular mechanisms. Through pseudotime trajectory analysisunique drug‐resistant cellular states associated with poor patient outcomes are revealed. Furthermore, DrugFormer identifies potential therapeutic targets, such as COX8A, for overcoming drug resistance across different cancer types. In conclusion, DrugFormer represents a significant advancement in the field of drug resistance prediction, offering a powerful tool for unraveling the heterogeneity of cellular response to drugs and guiding personalized treatment strategies. [ABSTRACT FROM AUTHOR]

With the widespread application of computer-aided technologies such as CAD and CAM in the manufacturing industry, a growing number of process documents and design documents generate multi-source process knowledge and expert experience. However, due to the diverse and complex representation of process knowledge, there is a need for more effective methods to mine a large amount of multi-source information and to exploit the explicit and implicit relationships between the knowledge contained in process knowledge. Effective knowledge reuse in process planning still needs to be improved. This paper proposes a reinforcement learning approach that combines knowledge graphs and process decision-making activities in process planning to exploit the learning potential of process knowledge graphs. Firstly, a reinforcement learning environment for process planning is introduced to model the process planning decision-making phase as a sequential recommendation of process knowledge. Then, this paper designs in detail the state representation method that combines process decision sequences and potential relationships between processes. This paper also creates the composite reward function that combines the process planning environment. In addition, a new algorithm is proposed for learning the proposed model more efficiently. Experimental results show that the network structure has more accurate recommendation results than other methods. [ABSTRACT FROM AUTHOR]

Multiple Choice Questions (MCQs) are an important evaluation technique for both examinations and learning activities. However, the manual creation of questions is time-consuming and challenging for teachers. Hence, there is a notable demand for an Automatic Question Generation (AQG) system. Several systems have been created for this aim, but the generated questions failed to meet the requirements for student assessment effectively. Consequently, research in education technology, natural language processing, and KG development technology to support the AQG systems is still in its infancy. In this paper, the innovative integrated AQG framework for creating MCQs with difficulty levels is presented. The improved KG is first built as a source for question generation through corresponding queries. The distractors or wrong choices are generated by proposing a unified difficulty ranking mechanism, which includes the hybrid technique of WordNet-based and Linked Data (LD)-based semantic similarity together with property filtering score. Furthermore, the syntactic feature i.e. part-of-speech is utilized for the best distractors generation. The experimental results of the proposed unified difficulty ranking mechanism demonstrate an accuracy of 94% on the KG test dataset and 75% on public datasets. The accuracy of distractors' correctness is 60% on the test dataset while it is 72% on the public dataset. The results highlight the efficiency of the proposed unified difficulty ranking mechanism for automatic MCQs generation in the digital storytelling domain. [ABSTRACT FROM AUTHOR]

The full implementation of MOOCs in online education offers new opportunities for integrating multidisciplinary and comprehensive STEM education. It facilitates the alignment between online learning content and learning behaviors. However, it also presents new challenges, such as a high rate of STEM dropouts. Many learners struggle to establish effective learning behaviors and fail to complete the entire learning process. This study focuses on analyzing a vast amount of MOOCs learning behavior instances and proposes a knowledge graph-based analysis and prediction model that is centered around associated STEM concepts. The objective is to provide key insights for fostering sustainable and efficient learning behaviors. By constructing a heterogeneous information network, analyzing and learning from key concepts and their relationships by the improved graph convolution neural networks, and employing adaptive recommendations based on the course-concept matrix, it is possible to generate knowledge graphs from extensive learning behavior instances, both within single course and across multiple courses. This approach accurately captures learning behavior patterns and provides guidance for effective learning paths. The data analysis process and predictive results demonstrate that the knowledge graph can effectively guide learning behaviors and enhance learning outcomes. This research offers technical support and a decision-making foundation for optimizing interdisciplinary learning process within MOOCs for STEM education. It showcases strong innovation and practicality. [ABSTRACT FROM AUTHOR]