Knowledge Representation Learning Research Articles

Knowledge is power: Open-world knowledge representation learning for knowledge-based visual reasoning

Knowledge-based visual reasoning requires the ability to associate outside knowledge that is not present in a given image for cross-modal visual understanding. Two deficiencies of the existing approaches are that (1) they only employ or construct elementary and explicit but superficial knowledge graphs while lacking complex and implicit but indispensable cross-modal knowledge for visual reasoning, and (2) they also cannot reason new/unseen images or questions in open environments and are often violated in real-world applications. How to represent and leverage tacit multimodal knowledge for open-world visual reasoning scenarios has been less studied. In this paper, we propose a novel open-world knowledge representation learning method to not only construct implicit knowledge representations from the given images and their questions but also enable knowledge transfer from a known given scene to an unknown scene for answer prediction. Extensive experiments conducted on six benchmarks demonstrate the superiority of our approach over other state-of-the-art methods. We apply our approach to other visual reasoning tasks, and the experimental results show that our approach, with its good performance, can support related reasoning applications.

A Condition Knowledge Representation and Feedback Learning Framework for Dynamic Optimization of Integrated Energy Systems.

An optimal energy scheduling strategy for integrated energy systems (IESs) can effectively improve the energy utilization efficiency and reduce carbon emissions. Due to the large-scale state space of IES caused by uncertain factors, it would be beneficial for the model training process to formulate a reasonable state-space representation. Thus, a condition knowledge representation and feedback learning framework based on contrastive reinforcement learning is designed in this study. Considering that different state conditions would bring inconsistent daily economic costs, a dynamic optimization model based on deterministic deep policy gradient is established, so that the condition samples can be partitioned according to the preoptimized daily costs. In order to represent the overall conditions on a daily basis and constrain the uncertain states in the IES environment, the state-space representation is constructed by a contrastive network considering the time dependence of variables. A Monte-Carlo policy gradient-based learning architecture is further proposed to optimize the condition partition and improve the policy learning performance. To verify the effectiveness of the proposed method, typical load operation scenarios of an IES are used in our simulations. The human experience strategies and state-of-the-art approaches are selected for comparisons. The results validate the advantages of the proposed approach in terms of cost effectiveness and ability to adapt in uncertain environments.

A multi-view heterogeneous knowledge learning method for personalized POI recommendation

Existing POI recommendation methods often fail to capture the fine-grained preferences of users and face the challenge of modeling multiple relationships. Moreover, knowledge graph-based recommendation methods are limited in storing dynamic user trajectories, making them unsuitable for POI recommendation scenarios. In this paper, we propose a Multi-View Heterogeneous Knowledge learning model that utilizes techniques for heterogeneous knowledge representation learning and multi-view context modeling. Our model comprehensively models user preferences and the relationships between users and POIs by utilizing information from users’ visiting sequences and POI attributes knowledge graph. Specifically, we design a heterogeneous knowledge embedding method to learn the representation of users and POIs using POI attribute knowledge and users’ visiting sequences. Additionally, we constructed a user trajectory similarity graph and a POI attribute similarity graph to explore potential relations between users and between POIs. The former measures the similarity of user behaviors based on user visit sequences, and the latter quantifies the similarity between different POIs through a novel feature mapping method. Finally, we propose a multi-view hybrid learning method that combines unsupervised and supervised learning paradigms to model complex relationships, improving the overall recommendation performance. Extensive experiments on real-world datasets validate the effectiveness of our method.

A Novel Method for Boosting Knowledge Representation Learning in Entity Alignment through Triple Confidence

A Novel Method for Boosting Knowledge Representation Learning in Entity Alignment through Triple Confidence

Incorporating environmental knowledge embedding and spatial-temporal graph attention networks for inland vessel traffic flow prediction

Accurate prediction of vessel traffic flow is crucial for maritime regulatory authorities and transportation planners. However, existing methods for inland vessel traffic flow prediction often overlook spatial correlation and environmental influences, leading to suboptimal accuracy. To address this issue, we propose an innovative model that incorporates environmental knowledge embedding and a spatial-temporal information extraction module. Our approach involves constructing a vessel traffic knowledge graph, embedding traffic flow through knowledge representation learning. The spatial-temporal information extraction module is leveraged to analyze inherent periodicity and external spatial relationships in vessel traffic flow. Extensive experiments on real-world datasets demonstrate that our approach significantly enhances predictive accuracy. In comparison to the second-ranked model, our approach achieves a decrease of 0.46 in mean absolute error, a decrease of 0.64 in root mean squared error, an increase of 3.06% in accuracy, and an increase of 0.07 in R-squared. Furthermore, our approach excels in upstream, downstream and long-term prediction, and displays robustness in handling noisy data.

A Survey of Knowledge Enhanced Pre-trained Language Models

Pre-trained language models learn informative word representations on a large-scale text corpus through self-supervised learning, which has achieved promising performance in fields of natural language processing (NLP) after fine-tuning. These models, however, suffer from poor robustness and lack of interpretability. We refer to pre-trained language models with knowledge injection as knowledge-enhanced pre-trained language models (KEPLMs). These models demonstrate deep understanding and logical reasoning and introduce interpretability. In this survey, we provide a comprehensive overview of KEPLMs in NLP. We first discuss the advancements in pre-trained language models and knowledge representation learning. Then we systematically categorize existing KEPLMs from three different perspectives. Finally, we outline some potential directions of KEPLMs for future research.

Toward a framework of extracting typical machining process routines based on knowledge representation learning

With the application of CAPP systems, manufacturing enterprises have accumulated a large volume of process data of parts, which are important strategic resources. Deeply mining the value hidden in these process data to improve the reuse rate of process knowledge is the key to realize the intellectualization of process planning. This paper builds a novel framework of extracting typical machining process routines (TMPRs) based on knowledge representation learning. First, two graph models, which describe machining processes including the relationships among “part-material-process-machine tool-cutting tool”, are established to present the semantic meaning of process data through the connectivity of graph structures in a direct way. One model conforms to the standard process routes, while the other makes some modifications to make the node “parts” have more in-links and out-links. Then, TransD algorithm is used to map the entities and relations based on the two models into dense low-dimensional real-valued spaces, and the better model is determined. After that, the vectors representing the parts of the better model are clustered, and the results show that the parts with a similar operation sequence and processed by the same cutting tools and machine tools can be clustered into the same cluster. This method breaks through the singleness and limitation of the traditional classification depending on the features of parts. Furthermore, TMPRs are extracted from the cluster results to verify the expression ability of semantic meaning of these vectors. Finally, we package the main functions of the research results into corresponding software modules. Compared with the existing process reuse methods, the proposed framework is much more efficient and extensible.

CoolGust: knowledge representation learning with commonsense knowledge guidelines and constraints

CoolGust: knowledge representation learning with commonsense knowledge guidelines and constraints

Theoretical Advancement of Xi Jinping’s Socialist Thought with Chinese Characteristics in the New Era under the Construction of Knowledge Map

Abstract This paper discusses the theory and practice of constructing knowledge graph under the guidance of Xi Jinping’s socialist thought with Chinese characteristics in the new era. The study first adopts the Transformer technique based on the BERT model for effectively extracting entity relationships. Then, the article proposes an entity alignment method based on Neural Tensor Network, which enhances the semantic and structural information utilization of entity embedding vectors through optimized NTN and joint knowledge representation learning. In addition, the study employs a knowledge graph link prediction method that combines semantics and paths to fill in missing relations, and applies probabilistic soft logic to solve the inference problem of non-deterministic knowledge. Ultimately, the effectiveness of the constructed knowledge graph is demonstrated through empirical analysis of Xi Jinping’s theoretical dataset of socialist thought with Chinese characteristics in the new era. The results show that the method is more effective in dealing with polysemous words and participle errors than traditional methods, improving the data structuring level. For example, the accuracy of entity alignment is significantly better than the baseline algorithm on different datasets, e.g., on the DBP-WE dataset, its Hits@1, Hits@10 and MRR values are higher than those of the baseline by 4.01-29.49, 1.99-31.05, and 0.036-0.289, respectively. The method of this paper is remarkably effective in improving the performance of the entity alignment task, which is helpful in understanding and applying the Xi Jinping’s thought of socialism with Chinese characteristics in the new era provides new theoretical perspectives and practical methods.

A Study of Minority Culture Outreach Translation Based on Cognitive Mapping Construction

Abstract In this paper, we first construct a cognitive neural network and use the knowledge representation learning technique for knowledge complementation and relation extraction to semantically match head-tail entity pairs with relations and accurately model the semantic relationships between entities and relations. Then, the vectors of each entity are mapped onto the hyperplane of a given relation by the cognitive mapping translation model, and vector translation operations are performed on the hyperplane. Finally, this paper’s translation model is compared with other models to compare the semantic representation translation, task processing function, and model complexity of each model so as to verify the superiority of this paper’s model for minority culture outreach translation. The results show that this paper’s method increases 3.4 and 1.2 BLEU values on average in the four translation tasks compared to the Imagination model and VAG model, respectively. When the number of iterations is 40, the MRR value of this paper’s model is 0.345, which is at least 0.1-0.5 more than the other models, thus indicating that this paper’s model has a better performance in outreach translation.

Using TransR to enhance drug repurposing knowledge graph for COVID-19 and its complications

MotivationThe COVID-19 pandemic has been spreading globally for four years, yet specific drugs that effectively suppress the virus remain elusive. Furthermore, the emergence of complications associated with COVID-19 presents significant challenges, making the development of therapeutics for COVID-19 and its complications an urgent task. However, traditional drug development processes are time-consuming. Drug repurposing, which involves identifying new therapeutic applications for existing drugs, presents a viable alternative. ResultIn this study, we construct a knowledge graph by retrieving information on genes, drugs, and diseases from databases such as DRUGBANK and GNBR. Next, we employ the TransR knowledge representation learning approach to embed entities and relationships into the knowledge graph. Subsequently, we train the knowledge graph using a graph neural network model based on TransR scoring. This trained knowledge graph is then utilized to predict drugs for the treatment of COVID-19 and its complications. Based on experimental results, we have identified 15 drugs out of the top 30 with the highest success rates associated with treating COVID-19 and its complications. Notably, out of these 15 drugs, 10 specifically aimed at treating COVID-19, such as Torcetrapib and Tocopherol, has not been previously identified in the knowledge graph. This finding highlights the potential of our model in aiding healthcare professionals in drug development and research related to this disease.

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.

The impact of artificial intelligence systems and technology on the sustainability of the quality of financial reports

The research aims to identify the concept of sustainability in financial reports and the arguments against and in favor of it when applied in business companies. Identify the factors affecting the process of sustaining the quality of financial reports Identify artificial intelligence techniques and know the expected impact of their application on business companies. Clarify the role of artificial intelligence techniques on the sustainability of the quality of financial reports. To achieve the objectives of the research The researcher organized a questionnaire form that included the main axes of artificial intelligence and the extent of its impact on the sustainability of the quality of financial reports, and the research reached several results, the most important of which is that artificial intelligence is one of the most important technologies that have the impact of the value and usefulness of the information shown by financial reports in a fast way and with a distinctive presentation, which makes it more expensive and enhances the sustainability of the quality of financial reports. The application of artificial intelligence systems and techniques is important and inevitable in the field of accounting, which will lead to high quality and continuity in the validity of information, which in turn will lead to the sustainability and quality of financial reports. The research recommended several recommendations, the most important of which is to enhance the use and application of artificial intelligence systems and techniques in economic units to raise the efficiency of accounting operations, which in turn enhances the sustainability of the quality of financial reports. Economic units should provide adequate assistance to the components of artificial intelligence from expert systems, knowledge representation and automatic learning in acquiring knowledge stored in databases that help raise the efficiency of information and the sustainability of the quality of financial reports.

A Network Representation Learning Model Based on Multiple Remodeling of Node Attributes

Current network representation learning models mainly use matrix factorization-based and neural network-based approaches, and most models still focus only on local neighbor features of nodes. Knowledge representation learning aims to learn low-dimensional dense representations of entities and relations from structured knowledge graphs, and most models use the triplets to capture semantic, logical, and topological features between entities and relations. In order to extend the generalization capability of the network representation learning models, this paper proposes a network representation learning algorithm based on multiple remodeling of node attributes named MRNR. The model constructs the knowledge triplets through the textual association relationships between nodes. Meanwhile, a novel co-occurrence word training method has been proposed. Multiple remodeling of node attributes can significantly improve the effectiveness of network representation learning. At the same time, MRNR introduces the attention mechanism to achieve the weight information for key co-occurrence words and triplets, which further models the semantic and topological features between entities and relations, and it makes the network embedding more accurate and has better generalization ability.

The joint knowledge reasoning model based on knowledge representation learning for aviation assembly domain

The joint knowledge reasoning model based on knowledge representation learning for aviation assembly domain

Inferring Complementary and Substitutable Products Based on Knowledge Graph Reasoning

Complementarity and substitutability between products are essential concepts in retail and marketing. To achieve this, existing approaches take advantage of knowledge graphs to learn more evidence for inference. However, they often omit the knowledge that lies in the unstructured data. In this research, we concentrate on inferring complementary and substitutable products in e-commerce from mass structured and unstructured data. An improved knowledge-graph-based reasoning model has been proposed which cannot only derive related products but also provide interpretable paths to explain the relationship. The methodology employed in our study unfolds through several stages. First, a knowledge graph refining entities and relationships from data was constructed. Second, we developed a two-stage knowledge representation learning method to better represent the structured and unstructured knowledge based on TransE and SBERT. Then, the relationship inferring problem was converted into a path reasoning problem under the Markov decision process environment by learning a dynamic policy network. We also applied a soft pruning strategy and a modified reward function to improve the effectiveness of the policy network training. We demonstrate the effectiveness of the proposed method on standard Amazon datasets, and it gives about 5–15% relative improvement over the state-of-the-art models in terms of NDCG@10, Recall@10, Precision @10, and HR@10.

Vehicle Trajectory Completion for Automatic Number Plate Recognition Data: A Temporal Knowledge Graph-Based Method

Vehicle trajectories represent an essential information source in intelligent transportation systems. Prior trajectory completion models based on Automatic Number Plate Recognition (ANPR) data have typically depended on vehicle re-identification results or road network information or have employed static knowledge graphs to integrate the two information sources. However, these methods have not taken into account the implicit temporal characteristics of trajectories in ANPR data and have neglected individual vehicle preferences. To address this void, this study proposes a Temporal Knowledge Graph-based Vehicle Trajectory Completion Model (TKG-VTC). The model implementation comprises three stages: first, ANPR data are converted into a temporal trajectory knowledge graph; second, knowledge representation learning is conducted using nontemporal relations, a biased temporal regularizer and multivector embeddings to embed the knowledge on the graph; and finally, the embedded results are employed to perform link prediction for incomplete trajectories, thereby restoring vehicle trajectories in ANPR data. Through model evaluation metrics and dimensionality reduction experiments, TKG-VTC is observed to demonstrate the best performance in completing trajectories when compared to TComplEx, TNTComplEx, and TeLM. This research introduces an innovative application of employing temporal knowledge graphs for trajectory reconstruction, which eliminates dependence on vehicle re-identification and road network information in previous methodologies. This is advantageous for enhancing the performance and dependability of vehicle trajectory data in intelligent transportation systems, as well as facilitating the implementation of trajectory prediction, demand analysis, and accident warning applications.

Constructing negative samples via entity prediction for multi-task knowledge representation learning

Knowledge representation learning (KRL) aims at embedding the entities and relations in knowledge graphs (KGs) into vectors by learning. In recent years, several multi-task learning (MTL) frameworks were proposed to KRL and achieved promising results. Nevertheless, most of these models only share the initial embeddings of entities and relations among sub-tasks. We construct hard negative samples for relation prediction (RP) task and triple classification (TC) task by using the similarity matrix from the entity prediction (EP) task. We also share the features in hidden layers of EP task to TC. The proposed framework is applicable to CNN based models for KRL. Experimental results on WN18RR and FB15k-237 datasets show that the proposed framework promotes the performance of EP, RP and TC tasks evidently comparing with the single task models and obtains better results in RP and TC than the state-of-the-art MTL-based models/frameworks. Code of NS-KRL is available online.11https://github.com/fofilix/NS_KRL.

TransRFT: A Knowledge Representation Learning Model Based on a Relational Neighborhood and Flexible Translation

The use of knowledge graphs has grown significantly in recent years. However, entities and relationships must be transformed into forms that can be processed by computers before the construction and application of a knowledge graph. Due to its simplicity, effectiveness, and great interpretability, the translation model lead by TransE has garnered the most attention among the many knowledge representation models that have been presented. However, the performance of this model is poor when dealing with complex relations such as one-to-many, many-to-one, and reflexive relations. Therefore, a knowledge representation learning model based on a relational neighborhood and flexible translation (TransRFT) is proposed in this paper. Firstly, the triples are mapped to the relational hyperplane using the idea of TransH. Then, flexible translation is applied to relax the strict restriction h + r = t in TransE. Finally, the relational neighborhood information is added to further improve the performance of the model. The experimental results show that the model has good performance in triplet classification and link prediction.

SRSCL: A strong-relatedness-sequence-based fine-grained collective entity linking method for heterogeneous information networks

The development of efficient methods for mining information from heterogeneous information networks (HINs) has become essential for improving the accuracy of collective entity linking in the absence of third-party knowledge bases. Currently, there remain three major challenges in the latest research: (1) The objective function of collective entity linking does not fully embrace the concept of “collective linking”. (2) The objective function employs the mean value rather than the maximum value of the entity relatedness as a link parameter, while discounting the importance of the strong logical associations between the text and language for meaning recognition. (3) The objective function utilizes only one type of 2-hop path to contribute to entity relatedness, thereby disregarding other types of 2-hop path that exist in actual HINs. To address the aforementioned issues, this paper proposes a strong-relatedness-sequence-based fine-grained collective entity linking method (SRSCL). The SRSCL is capable of capturing the contextual information of the entity in the HINs, thereby providing improved accuracy in entity linking. Specifically, SRSCL constructs a knowledge representation learning model and proposes an overall semantic similarity model for entity mentions and candidate entities to solve the objective function and thereby reflect the idea of “collective linking”. Additionally, a strong-relatedness-sequence-based overall relatedness measurement model is proposed for candidate entities to emphasize the strong logical associations between them. Furthermore, SRSCL defines three types of 2-hop path and evaluates the importance of each path to accurately measure the relatedness of entities. Finally, the experimental results demonstrate that the proposed SRSCL is more effective in capturing the overall relatedness of entities than the latest model. Particularly, when the number of entity mentions contained in one sliding window is greater than 6, the proposed SRSCL improves the precision, recall and F1 score by more than 10% compared with the latest model.