Article
Computer Science, Artificial Intelligence
Mei Yu, Qianyu Zhang, Jian Yu, Mankun Zhao, Xuewei Li, Di Jin, Ming Yang, Ruiguo Yu
Summary: Knowledge graphs are semantic networks designed to describe real-world facts. Existing graphs are incomplete, hence the need for knowledge graph completion. However, current graph completion models have limitations in distinguishing relations and aggregating multi-perspective features.
KNOWLEDGE-BASED SYSTEMS
(2023)
Article
Computer Science, Theory & Methods
Guojia Wan, Zhengyun Zhou, Zhigao Zheng, Bo Du
Summary: Existing large-scale knowledge graphs often have spatial and temporal information. However, current methods for knowledge graph completion often neglect the simultaneous modeling of spatial and temporal information, limiting their ability to infer knowledge related to time and location. This paper proposes a solution by using quintuple representation and sub-entity tokenization, along with a Spatio-Temporal Message Passing layer to learn latent feature vectors. Experimental results show the effectiveness of the model in predicting missing knowledge and capturing meaningful time and location information.
FUTURE GENERATION COMPUTER SYSTEMS-THE INTERNATIONAL JOURNAL OF ESCIENCE
(2023)
Article
Computer Science, Information Systems
Linyu Li, Xuan Zhang, Zhi Jin, Chen Gao, Rui Zhu, Yuqin Liang, Yubing Ma
Summary: Knowledge graph completion tasks aim to learn known facts and infer missing entities. This study proposes a new method, QIQE-KGC, which uses quantum embedding and quaternion space interaction to capture logical relationships and enhance connections between entities. Experimental results show outstanding performance on multiple datasets.
INFORMATION SCIENCES
(2023)
Article
Multidisciplinary Sciences
Peng He, Gang Zhou, Yao Yao, Zhe Wang, Hao Yang
Summary: This article proposes a new framework called TaKE, which enhances traditional KGE models by utilizing type features and introduces a new type-constrained negative sampling strategy to improve the performance of KG completion.
SCIENTIFIC REPORTS
(2023)
Article
Computer Science, Artificial Intelligence
Jingchao Wang, Weimin Li, Wei Liu, Can Wang, Qun Jin
Summary: Knowledge graph completion aims to fill in missing entities and relations in a knowledge graph. Existing inductive KG embedding methods can embed unseen entities, but they do not fully utilize the structural information of neighbors or handle unseen relations. In this paper, we propose a novel inductive KGC model called SAAN, which can generate embeddings of unseen entities and relations by aggregating neighbors with structure-aware attention weights. Experimental results show that our model outperforms state-of-the-art methods in both transductive and inductive KGC tasks.
APPLIED INTELLIGENCE
(2023)
Article
Computer Science, Artificial Intelligence
Juan Li, Wen Zhang, Hongtao Yu
Summary: In this paper, relation-free knowledge graph completion is investigated to predict relation-tail (r-t) pairs given a head entity. A multi-view filter is proposed to filter r-t pairs, which includes two intra-view modules and an inter-view module. Experimental results show the efficiency of this method in preserving higher-quality candidate r-t pairs for knowledge graphs and resulting in better relation-free knowledge graph completion.
Article
Chemistry, Multidisciplinary
Xiaochun Sun, Chenmou Wu, Shuqun Yang
Summary: With the proliferation of Knowledge Graphs (KGs), knowledge graph completion (KGC) has attracted much attention. Previous methods focused on extracting shallow structural information from KGs or combining with external knowledge. To address the limitations, a novel Scalable Formal Concept-driven Architecture (SFCA) was proposed to encode factual triples into formal concepts, providing valuable information for KGC. Comprehensive experiments on public datasets and industry dataset demonstrated the effectiveness and scalability of SFCA, offering new ideas for the promotion and application of knowledge graphs in AI downstream tasks.
APPLIED SCIENCES-BASEL
(2023)
Article
Computer Science, Artificial Intelligence
Weidong Li, Rong Peng, Zhi Li
Summary: This study proposes a novel knowledge graph embedding model named InterERP, which improves model performance by increasing interactions between the embeddings of entities, relations, and relation paths. Experimental results demonstrate that InterERP outperforms state-of-the-art methods on commonly used datasets.
APPLIED INTELLIGENCE
(2022)
Article
Computer Science, Artificial Intelligence
Jiapu Wang, Boyue Wang, Junbin Gao, Xiaoyan Li, Yongli Hu, Baocai Yin
Summary: This article introduces a novel TKGC method called the quadruplet distributor network (QDN), which independently models the embeddings of entities, relations, and timestamps to fully capture the semantics and uses a quadruplet-specific decoder for integration. A novel temporal regularization method is also proposed. Experimental results demonstrate the superior performance of the proposed method.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2023)
Article
Computer Science, Artificial Intelligence
Peng He, Gang Zhou, Hongbo Liu, Yi Xia, Ling Wang
Summary: Knowledge Graph embedding approaches have been proven effective in inferring new facts based on existing knowledge. However, most approaches have focused on static Knowledge Graphs, while relational facts in Knowledge Graphs often exhibit temporal dynamics. Therefore, developing temporal Knowledge Graph embedding models that utilize available time information is becoming increasingly important. This paper proposes a new hyperplane-based time-aware Knowledge Graph embedding model for temporal KG completion, which explicitly incorporates time information to effectively predict missing elements in the KG.
JOURNAL OF INTELLIGENT & FUZZY SYSTEMS
(2022)
Article
Computer Science, Information Systems
Yu Liu, Wen Hua, Jianfeng Qu, Kexuan Xin, Xiaofang Zhou
Summary: This paper proposes a novel approach to temporal knowledge graph embedding, leveraging temporal consistency and contextual consistency to capture specific interactions between target facts and contexts.
WORLD WIDE WEB-INTERNET AND WEB INFORMATION SYSTEMS
(2021)
Article
Computer Science, Artificial Intelligence
Weihang Zhang, Ovidiu Serban, Jiahao Sun, Yike Guo
Summary: This paper proposes a novel method for multiple knowledge graph completion by leveraging information from other knowledge graphs to alleviate the sparseness of a single knowledge graph, achieving state-of-the-art results on multilingual knowledge graph datasets.
KNOWLEDGE-BASED SYSTEMS
(2023)
Article
Computer Science, Artificial Intelligence
Jinglin Zhang, Bo Shen, Tao Wang, Yu Zhong
Summary: The parameter gamma plays a crucial role in distance-based knowledge graph embedding. It is usually considered a hyperparameter, but it may have continuous properties and complement other parameters. To explore gamma's characteristics, a multi-iterated parameterized scheme is proposed to convert it from a hyperparameter to a normal parameter. The macro and micro parameterized methods are provided to achieve this conversion. Experimental results show that the proposed scheme and methods can achieve similar or better results compared to the original method.
APPLIED INTELLIGENCE
(2023)
Article
Computer Science, Artificial Intelligence
Shuang Liang, Jie Shao, Dongyang Zhang, Jiasheng Zhang, Bin Cui
Summary: Recently, many knowledge graph embedding models have been proposed, but they only focus on semantic information and neglect graph structure information. To address this issue, a novel model called deep relational graph infomax (DRGI) is proposed, which combines complete structure information and semantic information. DRGI consists of two encoders, ARGATs, for capturing semantic and structure information respectively. The method achieves state-of-the-art performance and shows advantages in convergence speed and predictive performance for entities with small indegree.
IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING
(2023)
Article
Computer Science, Information Systems
Byungkook Oh, Seungmin Seo, Jimin Hwang, Dongho Lee, Kyong-Ho Lee
Summary: This paper proposes a novel Inductive KG Embedding (IKGE) model for open-world Knowledge Graph Completion (KGC), which addresses the challenges of handling evolving KGs and incorporating global graph-structured information. The IKGE model learns an embedding generator function and utilizes attention mechanism and neighborhood feature aggregation to improve the performance of KGC models. Experimental results demonstrate that IKGE outperforms existing approaches in both transductive and inductive setups.
INFORMATION SCIENCES
(2022)
Article
Computer Science, Artificial Intelligence
Hao Yang, Min Wang, Zhengfei Yu, Hang Zhang, Jinshen Jiang, Yun Zhou
Summary: In this paper, a novel method called CSTTA is proposed for test time adaptation (TTA), which utilizes confidence-based optimization and sample reweighting to better utilize sample information. Extensive experiments demonstrate the effectiveness of the proposed method.
KNOWLEDGE-BASED SYSTEMS
(2024)
Article
Computer Science, Artificial Intelligence
Jin Liu, Ju-Sheng Mi, Dong-Yun Niu
Summary: This article focuses on a novel method for generating a canonical basis for decision implications based on object-induced operators (OE operators). The logic of decision implication based on OE operators is described, and a method for obtaining the canonical basis for decision implications is given. The completeness, nonredundancy, and optimality of the canonical basis are proven. Additionally, a method for generating true premises based on OE operators is proposed.
KNOWLEDGE-BASED SYSTEMS
(2024)
Review
Computer Science, Artificial Intelligence
Kun Bu, Yuanchao Liu, Xiaolong Ju
Summary: This paper discusses the importance of sentiment analysis and pre-trained models in natural language processing, and explores the application of prompt learning. The research shows that prompt learning is more suitable for sentiment analysis tasks and can achieve good performance.
KNOWLEDGE-BASED SYSTEMS
(2024)
Article
Computer Science, Artificial Intelligence
Xiangjun Cai, Dagang Li
Summary: This paper presents a new decomposition mechanism based on learned decomposition mapping. By using a neural network to learn the relationship between original time series and decomposed results, the repetitive computation overhead during rolling decomposition is relieved. Additionally, extended mapping and partial decomposition methods are proposed to alleviate boundary effects on prediction performance. Comparative studies demonstrate that the proposed method outperforms existing RDEMs in terms of operation speed and prediction accuracy.
KNOWLEDGE-BASED SYSTEMS
(2024)
Article
Computer Science, Artificial Intelligence
Xu Wu, Yang Liu, Jie Tian, Yuanpeng Li
Summary: This paper proposes a blockchain-based privacy-preserving trust management architecture, which adopts federated learning to train task-specific trust models and utilizes differential privacy to protect device privacy. In addition, a game theory-based incentive mechanism and a parallel consensus protocol are proposed to improve the accuracy of trust computing and the efficiency of consensus.
KNOWLEDGE-BASED SYSTEMS
(2024)
Article
Computer Science, Artificial Intelligence
Zaiyang Yu, Prayag Tiwari, Luyang Hou, Lusi Li, Weijun Li, Limin Jiang, Xin Ning
Summary: This study introduces a 3D view-based approach that effectively handles occlusions and leverages the geometric information of 3D objects. The proposed method achieves state-of-the-art results on occluded ReID tasks and exhibits competitive performance on holistic ReID tasks.
KNOWLEDGE-BASED SYSTEMS
(2024)
Article
Computer Science, Artificial Intelligence
Yongliang Shi, Runyi Yang, Zirui Wu, Pengfei Li, Caiyun Liu, Hao Zhao, Guyue Zhou
Summary: Neural implicit representations have gained attention due to their expressive, continuous, and compact properties. However, there is still a lack of research on city-scale continual implicit dense mapping based on sparse LiDAR input. In this study, a city-scale continual neural mapping system with a panoptic representation is developed, incorporating environment-level and instance-level modeling. A tailored three-layer sampling strategy and category-specific prior are proposed to address the challenges of representing geometric information in city-scale space and achieving high fidelity mapping of instances under incomplete observation.
KNOWLEDGE-BASED SYSTEMS
(2024)
Article
Computer Science, Artificial Intelligence
Ruihan Hu, Zhi-Ri Tang, Rui Yang, Zhongjie Wang
Summary: Mesh data is crucial for 3D computer vision applications worldwide, but traditional deep learning frameworks have struggled with handling meshes. This paper proposes MDSSN, a simple mesh computation framework that models triangle meshes and represents their shape using face-based and edge-based Riemannian graphs. The framework incorporates end-to-end operators inspired by traditional deep learning frameworks, and includes dedicated modules for addressing challenges in mesh classification and segmentation tasks. Experimental results demonstrate that MDSSN outperforms other state-of-the-art approaches.
KNOWLEDGE-BASED SYSTEMS
(2024)
Article
Computer Science, Artificial Intelligence
Buliao Huang, Yunhui Zhu, Muhammad Usman, Huanhuan Chen
Summary: This paper proposes a novel semi-supervised conditional normalizing flow (SSCFlow) algorithm that combines unsupervised imputation and supervised classification. By estimating the conditional distribution of incomplete instances, SSCFlow facilitates imputation and classification simultaneously, addressing the issue of separated tasks ignoring data distribution and label information in traditional methods.
KNOWLEDGE-BASED SYSTEMS
(2024)
Article
Computer Science, Artificial Intelligence
Deeksha Varshney, Asif Ekbal, Erik Cambria
Summary: This paper focuses on the neural-based interactive dialogue system that aims to engage and retain humans in long-lasting conversations. It proposes a new neural generative model that combines step-wise co-attention, self-attention-based transformer network, and an emotion classifier to control emotion and knowledge transfer during response generation. The results from quantitative, qualitative, and human evaluation show that the proposed models can generate natural and coherent sentences, capturing essential facts with significant improvement over emotional content.
KNOWLEDGE-BASED SYSTEMS
(2024)
Article
Computer Science, Artificial Intelligence
Junchen Ye, Weimiao Li, Zhixin Zhang, Tongyu Zhu, Leilei Sun, Bowen Du
Summary: Modeling multivariate time series has long been a topic of interest for scholars in various fields. This paper introduces MvTS, an open library based on Pytorch, which provides a unified framework for implementing and evaluating these models. Extensive experiments on public datasets demonstrate the effectiveness and universality of the models reproduced by MvTS.
KNOWLEDGE-BASED SYSTEMS
(2024)
Article
Computer Science, Artificial Intelligence
Reham R. Mostafa, Ahmed M. Khedr, Zaher Al Aghbari, Imad Afyouni, Ibrahim Kamel, Naveed Ahmed
Summary: Feature selection is crucial in classification procedures, but it faces challenges in high-dimensional datasets. To overcome these challenges, this study proposes an Adaptive Hybrid-Mutated Differential Evolution method that incorporates the mechanics of the Spider Wasp Optimization algorithm and the concept of Enhanced Solution Quality. Experimental results demonstrate the effectiveness of the method in terms of accuracy and convergence speed, and it outperforms contemporary cutting-edge algorithms.
KNOWLEDGE-BASED SYSTEMS
(2024)
Article
Computer Science, Artificial Intelligence
Ti Xiang, Pin Lv, Liguo Sun, Yipu Yang, Jiuwu Hao
Summary: This paper introduces a Track Classification Model (TCM) based on marine radar, which can effectively recognize and classify shipping tracks. By using a feature extraction network with multi-feature fusion and a dataset production method to address missing labels, the classification accuracy is improved, resulting in successful engineering application in real scenarios.
KNOWLEDGE-BASED SYSTEMS
(2024)
Article
Computer Science, Artificial Intelligence
Zhihao Zhang, Yuan Zuo, Chenghua Lin, Junjie Wu
Summary: This paper proposes a novel unsupervised context-aware quality phrase mining framework called LMPhrase, which is built upon large pre-trained language models. The framework mines quality phrases as silver labels using a parameter-free probing technique on the pre-trained language model BERT, and formalizes the phrase tagging task as a sequence generation problem by fine-tuning on the Sequence to-Sequence pre-trained language model BART. The results of extensive experiments show that LMPhrase consistently outperforms existing competitors in two different granularity phrase mining tasks.
KNOWLEDGE-BASED SYSTEMS
(2024)
Article
Computer Science, Artificial Intelligence
Kemal Buyukkaya, M. Ozan Karsavuran, Cevdet Aykanat
Summary: The study aims to investigate the hybrid parallelization of the Stochastic Gradient Descent (SGD) algorithm for solving the matrix completion problem on a high-performance computing platform. A hybrid parallel decentralized SGD framework with asynchronous inter-process communication and a novel flexible partitioning scheme is proposed to achieve scalability up to hundreds of processors. Experimental results on real-world benchmark datasets show that the proposed algorithm achieves 6x higher throughput on sparse datasets compared to the state-of-the-art, while achieving comparable throughput on relatively dense datasets.
KNOWLEDGE-BASED SYSTEMS
(2024)