Modeling Relation Paths for Knowledge Graph Completion
The DOI matches its Crossref record; 55 of the 57 references it cites were found in a registry or an index.
Abstract
Knowledge graphs (KG) often encounter knowledge incompleteness. The path reasoning that predicts the unknown path relation between pairwise entities based on existing facts is one of the most promising approaches to the knowledge graph completion. However, most conventional path reasoning methods exclusively consider the entity description included in fact triples, ignoring both the type information of entities and the interaction between different semantic representations. In this study, we propose a novel method, Type-aware Attentive Path Reasoning (TAPR), to complete the knowledge graph by simultaneously considering KG structural information, textual information, and type information. More specifically, we first leverage types to enrich the representational learning of entities and relationships. Next, we describe a type-level attention to select the most relevant type of given entity in a specific triple without any predefined rules or patterns to reduce the impact of noisy types. After learning the distributed representation of all paths, path-level attention assigns different weights to paths, from which relations among entity pairs are calculated. We conduct a series of experiments on a real-world dataset to demonstrate the effectiveness of TAPR. Experimental results show that our method significantly outperforms all baselines on link prediction and entity prediction tasks.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“Therefore, YOLOv8 is the newest and most effective object detector based on convolution layers [37,38].”
From Vehicle Detection and Classification via YOLOv8 and Deep Belief Network over Aerial Image Sequences (2023) · cites this paper as [38]
Citations
Cites
Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation
Cho, K., van Merrienboer, B., Gulcehre, C., Bahdanau, D., Bougares, F., Schwenk, H., & Bengio, Y. (2014) · Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.3115/v1/d14-1179 · Cited by 25,545
WordNet: a lexical database for English
Miller, G. A. (1995) · Communications of the ACM · doi:10.1145/219717.219748 · Cited by 14,015
Berners-Lee, T., Hendler, J., & Lassila, O. (2001) · Scientific American · doi:10.1038/scientificamerican0501-34 · Cited by 8,651
(2013) · Cited by 5,726
Freebase: a collaboratively created graph database for structuring human knowledge
Bollacker, K., Evans, C., Paritosh, P., Sturge, T., & Taylor, J. (2008) · Proceedings of the 2008 ACM SIGMOD international conference on Management of data · doi:10.1145/1376616.1376746 · Cited by 4,852
Knowledge Graph Embedding by Translating on Hyperplanes
Wang, Z., Zhang, J., Feng, J., & Chen, Z. (2014) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v28i1.8870 · Cited by 3,915
Learning Entity and Relation Embeddings for Knowledge Graph Completion
Lin, Y., Liu, Z., Sun, M., Liu, Y., & Zhu, X. (2015) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v29i1.9491 · Cited by 3,749
Wikidata: a free collaborative knowledgebase
Vrandečić, D., & Krötzsch, M. (2014) · Communications of the ACM · doi:10.1145/2629489 · Cited by 3,342
Knowledge Graph Embedding: A Survey of Approaches and Applications
Wang, Q., Mao, Z., Wang, B., & Guo, L. (2017) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2017.2754499 · Cited by 2,654
Yago: a core of semantic knowledge
Suchanek, F. M., Kasneci, G., & Weikum, G. (2007) · Proceedings of the 16th international conference on World Wide Web · doi:10.1145/1242572.1242667 · Cited by 2,512
Research works printed but not linked: 2
- xie, 2016, Representation learning of knowledge graphs with hierarchical types, Proc 25th Int Joint Conf Artif Intell, 2965
- deaton, 2005, The comprehensive terrorism knowledge base in CYC, Proc Int Conf Intell Anal, 1
Cited by
Items 101–155 of 155
Relation extraction in Chinese using attention-based bidirectional long short-term memory networks
Zhang, Y. (2023) · PeerJ Computer Science · doi:10.7717/peerj-cs.1509 · Cited by 4
“The integration of external linguistic knowledge was used to partially solve this issue ( Shen et al., 2021 ; Liu et al., 2023 ).”
Han, S., Ye, Q., Almadhor, A. S., & Abbas, M. A. (2023) · Mechanics of Advanced Materials and Structures · doi:10.1080/15376494.2023.2254760 · Cited by 4
“[80 – 82].”
DoreBer: Document-Level Relation Extraction Method Based on BernNet
Yuan, B., & Xu, L. (2023) · IEEE Access · doi:10.1109/access.2023.3337871 · Cited by 4
“…is widely used to facilitate a lot of downstream foundational tasks of Natural Language Processing (NLP) including knowledge base construction [1], [2], [3], knowledge graph completion [4], [5], [6], information retrieval [7], [8], [9], alignment [10], [11], [12], and question answering [13], [14].”
BackgroundRelation-dependent contrastive learning with cluster sampling for inductive relation prediction
Wu, J., Xiong, A., Mai, S., & Hu, H. (2024) · Neurocomputing · doi:10.1016/j.neucom.2024.127425 · Cited by 5
Modeling path information for knowledge graph completion
Shen, Y., Li, D., & Du, N. (2021) · Neural Computing and Applications · doi:10.1007/s00521-021-06460-2 · Cited by 4
“TAPR [21] A Type-aware Attentive Path Reasoning framework to complete the knowledge graph by simultaneously considering KG structural information, textual information, and type information Neural Computing and Applications (2022) 34:1951–1961 1957”
MethodInfluentialSelf-citationChen, L., Far, H., Mortazavi, M., & Ragab, A. E. (2023) · Buildings · doi:10.3390/buildings13082045 · Cited by 3
Link Prediction on N-ary Relational Data Based on Relatedness Evaluation
Navale, V. S., Jane, C., Anvita, B., Kalyan, B., & Satvik, A. (2023) · International Journal for Research in Applied Science and Engineering Technology · doi:10.22214/ijraset.2023.55413 · Cited by 3
Wang, S. (2025) · International Conference on Intelligent Systems and Computational Networks (ICISCN) · doi:10.1109/iciscn64258.2025.10934291 · Cited by 3
Incremental Survivability Enhancement in Mobile Crowdsensing Systems
Wang, J., Zhao, D., & Zhao, G. (2025) · IEEE Transactions on Network and Service Management · doi:10.1109/tnsm.2025.3598732 · Cited by 3
Zafarani-Moattar, E., Kangavari, M. R., & Rahmani, A. M. (2025) · IEEE Access · doi:10.1109/access.2025.3607164 · Cited by 3
Yu, H. Z., Tang, J., Peng, Z., & Wang, Y. (2024) · International Journal of Machine Learning and Cybernetics · doi:10.1007/s13042-024-02179-3 · Cited by 3
“To address this problem, Shen et al. [20] proposed a new approach, namely TAPR, which embeds knowledge graph by considering structural information, textual information and type information simultaneously.”
Amouzouvi, K., Chudasama, Y., Purohit, D., Rivas, A., Song, B., Lehmann, J., Vahdati, S., & Vidal, M.-E. (2025) · IEEE Access · doi:10.1109/access.2025.3564130 · Cited by 2
“We report in Tables 5-9 the experimental evaluation of the baseline KGE models and our model SimE on the French Royalty KG, the Family KG, YAGO3-10, WN18RR and their sub-graphs suffixed with 1:1, 1:N, N:1, N:M as well as seven synthetic KGs (Sierpinski and Quad). and topological patterns in the KGs.”
InfluentialChen, Y., Li, Z., Xiao, G., Xu, P., Zhang, X., & Li, K. (2025) · Science China Information Sciences · doi:10.1007/s11432-023-3916-0 · Cited by 2
RPND: a rule guided link prediction model with specific-path selection
Zheng, X., Li, P., Zhang, Z., & Wu, X. (2025) · Frontiers of Computer Science · doi:10.1007/s11704-025-41288-2 · Cited by 2
RETRACTED ARTICLE: Evaluating urban ecological wetland parks using big data analytics and art vision
Lu, C. (2023) · Soft Computing · doi:10.1007/s00500-023-09036-5 · Cited by 2
RetractedLeveraging Inference: A Regression-Based Learner Performance Prediction System for Knowledge Tracing
Sridhara, A., Falkner, N., & Atapattu, T. (2023) · IEEE Access · doi:10.1109/access.2023.3329571 · Cited by 2
“…for simplicity [13], [14], [15], [16], [17] and/or in the case of NN models interpretability and transferability for accuracy [18], [19], [20], [21] or require computationally expensive pre-processing [22], [23], [24], [25] or computationally expensive parameter estimation [26], [27], [28], [29].”
BackgroundMethodJaved, H. T., Khan, K. U., Cheema, M. F., Algarni, A. M., & Park, J. (2023) · IEEE Access · doi:10.1109/access.2023.3340984 · Cited by 2
“References [15] and [17] proposed an approach to summarize large semantics graphs using namespaces.”
Knowledge Representation and Reuse of Ship Block Coating Based on Knowledge Graph
Bu, H., Yang, P., Guo, Q., & Zhou, H. (2023) · Coatings · doi:10.3390/coatings14010024 · Cited by 2
Chen, C., & Chen, X.-X. (2024) · Aslib Journal of Information Management · doi:10.1108/ajim-01-2024-0014 · Cited by 2
SIKGC: Structural Information Prompt Based Knowledge Graph Completion with Large Language Models
Li, W., Ge, J., Feng, W., Zhang, L., Li, L., & Wu, B. (2024) · Conference proceedings/Conference proceedings - IEEE International Conference on Systems, Man, and Cybernetics · doi:10.1109/smc54092.2024.10831590 · Cited by 4
PEJL: A path-enhanced joint learning approach for knowledge graph completion
Lu, X., Wang, L., Jiang, Z., Liu, S., & Lin, J. (2023) · AIMS Mathematics · doi:10.3934/math.20231067 · Cited by 1
Alohali, M. A., Elsadig, M., Hilal, A. M., & Motwakel, A. (2023) · PeerJ Computer Science · doi:10.7717/peerj-cs.1596 · Cited by 1
“The approach likely involves designing a model that effectively captures and processes relation paths between entities in the knowledge graph ( Shen et al., 2020 ; Lu et al., 2023 ).”
MethodDistantly Supervised relation extraction with multi-level contextual information integration
Han, D., Huang, H., Shi, S., Yuan, C., & Guo, C. (2025) · Neurocomputing · doi:10.1016/j.neucom.2025.129858 · Cited by 1
Shabaz, M., & Soni, M. (2025) · Chinese journal of information fusion. · doi:10.62762/cjif.2025.197460 · Cited by 1
MP-NER: Morpho-Phonological Integration Embedding for Chinese Named Entity Recognition
Li, P., Cheng, G., Deng, G., Qu, S., Huang, M., & Li, G. (2025) · IEEE Access · doi:10.1109/access.2025.3565908 · Cited by 1
Graph Self-attention Mechanism for Interpretable Multi-hop Knowledge Graph Link Prediction
Liu, H., Li, D., Zeng, B., Liang, W., & Li, D. (2025) · ACM Transactions on Knowledge Discovery from Data · doi:10.1145/3737702 · Cited by 3
“(2) Shen et al. [31] found that the interpretability of paths comes mainly from relational paths rather than intermediate entities.”
Zhou, L., Gao, S., Zhang, H., & Liang, C. (2025) · SAE technical papers on CD-ROM/SAE technical paper series · doi:10.4271/2025-99-0049 · Cited by 1
T-NER: Triple embedding for Chinese Named Entity Recognition
Li, P., Cheng, G., Guo, Y., Jiang, Y., Li, G., Qu, S., & Ai, B. (2025) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn64981.2025.11229359 · Cited by 1
“It is widely used in the construction of knowledge graphs [5][6][7][8], question-and-answer systems [9], and pre-trained language models [10][11], among other downstream tasks.”
Liu, B., Zhang, Y., & Li, J. (2025) · Knowledge-Based Systems · doi:10.1016/j.knosys.2025.115006 · Cited by 1
Wang, Z., Zeng, L., Zhong, L., Wang, Y., Zhang, H., Gu, Z., & Zhang, Y. (2026) · IEEE Internet of Things Journal · doi:10.1109/jiot.2026.3661184 · Cited by 1
“KG, a method of structuring data representation, is composed of numerous triples (head entity → relation → tail entity) and is commonly used to complete triple reasoning tasks [13].”
Explainability-Guided Untargeted Attacks on Knowledge Graph Embedding
Lin, Y., Yu, H., Liang, K., Wang, M., Yang, L., & Liu, X. Y. (2026) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2026.3689651 · Cited by 1
“With the increasing demand for explain-ability in artificial intelligence, more and more researchers [26], [40], [41], [42] are focusing on the explainability of the knowledge graph.”
Discrete Whale Optimization Algorithm for Influence Maximization in Social Networks
Chen, W., Zhou, Y., & Luo, Q. (2026) · Concurrency and Computation Practice and Experience · doi:10.1002/cpe.70837 · Cited by 1
“Shen et al. [ 13] introduced an enhanced greedy algorithm that prunes weakly correlated edges to boost efficiency, while further optimizations to CELF significantly improved its performance in certain scenarios [ 14].”
Intelligent Customer Behaviour Analysis in the Norwegian Market
Brathovde, K., Djenouri, Y., Yazidi, A., & Srivastava, G. (2024) · IEEE International Conference on Data Engineering Workshops (ICDEW) · doi:10.1109/icdew61823.2024.00014 · Cited by 1
“Affinity analysis is an effective tool to enhance the consumers’ experience along with the company’s knowledge of their customers [15].”
MethodA Novel Robotic GWO LDI Modeling and Control for Nonlinear Systems
Zhang, E., Chen, Y., Chen, X., Zhang, J., Xu, P., & Zhuo, J. (2023) · The International Journal of Acoustics and Vibration · doi:10.20855/ijav.2023.28.21897
Yang, Q., Lü, Q., Ali, Y. A., & Al‐Razgan, M. (2023) · Mechanics Based Design of Structures and Machines · doi:10.1080/15397734.2023.2229913
“They revolutionize the way cities operate by enhancing efficiency (Li et al. 2022; Qiao, Li and Kong 2023), optimizing energy consumption (Han et al. 2023; Zenggang et al. 2022), and improving decision-making processes (Wu et al. 2023; Shen et al. 2021).”
BackgroundZhai, X., Liu, C., & Qiao, L. (2023) · Soft Computing · doi:10.1007/s00500-023-09127-3
“However, despite their cultural importance, most picture communication platforms in rural areas are developed and maintained by locals, often needing more sustainability and technical support (Shen et al. 2020).”
RetractedZhang, J., Rong, J., Zhang, C., & Li, Y. (2023) · Soft Computing · doi:10.1007/s00500-023-09222-5
“The output tracking error of the controlled system under the action of the algorithm proposed in this section converges faster, and the radius of the zero domains to which the output tracking error converges is smaller than that under the action of the comparison algorithm (Shen et al. 2021).”
Self-citationRetractedA Multi-View Information Fusion Relation Detection Model Based on Self-Attention for KbqaPreprint
Tong, G., Hu, Q., Yang, P., & Gao, L. (2023) · SSRN Electronic Journal · doi:10.2139/ssrn.4605360
On topological indices of third type of hex-derived networks
Ali, H., Ali, D. A., Liaqat, F., Yaseen, M. H., Khan, M. I., Ali, S., Al-Malki, N. A., & Abdullaeva, B. S. (2023) · Journal of Mathematical Chemistry · doi:10.1007/s10910-023-01555-8 · Cited by 1
“Guo et al. [12], Shen et al. [27], and Ni et al. [24] have recently emphasized the significance of diverse methodologies in social network analysis.”
Manufacturing Knowledge Graph-Based Disentangled Prediction Framework and Industrial Practices
Sui, Q., Wang, Y., & Liu, C. (2023) · International Conference on Robotics, Control and Automation Engineering (RCAE) · doi:10.1109/rcae59706.2023.10398819
“They serve as powerful tools for organizing, structuring, and representing complex manufacturing data and information [12, 13].”
BackgroundDomain-Specific Dictionary between Human and Machine Languages
Islam, M. S., & Liu, F. (2024) · Information · doi:10.3390/info15030144
Natural Language Processing for Text Mining: Leveraging Linguistic Features for Classification
Benitta., G., Asha, H. J., & Josephine, J. A. (2024) · International Conference on Emerging Smart Computing and Informatics (ESCI) · doi:10.1109/esci59607.2024.10497213
“Researcher [9] stressed knowing why models make certain choices is crucial, especially with tough jobs like sorting text.”
BackgroundStochastic shared embeddings and latent intent aware self-attention for sequential recommendation
Wu, D., Ma, W., & Yang, L. (2024) · Multimedia Tools and Applications · doi:10.1007/s11042-024-18657-3
Sequestered Shepherded Long-Tailed Intercommunication Eradication using Restraint Adumbration
Sanjay, S., & Nayak, L. (2024) · International Journal of Advanced Research in Science Communication and Technology · doi:10.48175/ijetir-1222
Confidence-based Modeling of Temporal Knowledge Graphs
Yang, B., Zhao, C., & Chen, S. (2024) · Guangdong-Hong Kong-Macao Greater Bay Area International Conference on Digital Economy and Artificial Intelligence (DEAI) · doi:10.1145/3675417.3675511
“To quantify relation-time path dependability, we employ the path-constrained resource allocation method, or PCRA [10].”
Lu, J., Ji, Y., & Zhang, T. (2024) · Asia-Pacific Conference on Image Processing, Electronics and Computers (IPEC) · doi:10.1109/ipec61310.2024.00111
“NN models have been applied in diverse domains, encompassing image remote sensing (RS) recognition, system ID, and others [13-15].”
A Study of LFT Embeddings in the Second Order Clifford Algebra Cl (R²,º)
Amouzouvi, K., Vahdati, S., Song, B., Bainson, B. O., Nishat, N. A. Z., & Lehmann, J. (2024) · IEEE Access · doi:10.1109/access.2024.3514303
“KGs are used in providing recommendation systems, question answering, entity classification and knowledge completion [1], [2], [3], [4], [5].”
A Knowledge Graph Completion Model with Path-Specific Learning
Zheng, X., Zhang, Z., Li, R., & Wu, X. (2024) · IEEE International Conference on Medical Artificial Intelligence (MedAI) · doi:10.1109/medai62885.2024.00071
“To this end, TAPR [30] completes this blank and considers path information, textual information and type information.”
D-NER: Double embedding for Chinese Named Entity Recognition
Cheng, G., Deng, G., Wang, S., Shang, F., Guo, Y., Wei, Y., & Li, P. (2025) · IEEE Joint International Information Technology and Artificial Intelligence Conference (ITAIC) · doi:10.1109/itaic64559.2025.11163037
“Additionally, Chinese features such as polysemy and the differing meanings of words across historical contexts further complicate the NER process[8].”
Xu, X., & Xu, H. (2025) · Applied Mathematics and Nonlinear Sciences · doi:10.2478/amns-2025-1123
Li, B., & Song, B. (2026) · Neurocomputing · doi:10.1016/j.neucom.2026.133740 · Cited by 1
Advancing knowledge graph reasoning through key feature fusion in logical message propagation
Zeng, Y., Hou, X., Wang, X. R., Li, J. C., Yang, J., & Liang, S. (2026) · Neurocomputing · doi:10.1016/j.neucom.2026.133894
Li, X., Wang, D., Yuan, J., Pan, Y. H., Liu, J., Cheng, J. C. P., & Chen, A. (2026) · Advanced Engineering Informatics · doi:10.1016/j.aei.2026.105034 · Cited by 2
HeLPormer: Heterogeneous graph transformer for link prediction
Fan, H., Fan, Z., Lu, Y., Jiao, P., & Ruan, N. (2026) · Physica A Statistical Mechanics and its Applications · doi:10.1016/j.physa.2026.132064
Wu, J., & Weng, W. (2026) · International Conference on Artificial Intelligence and Smart Manufacturing · doi:10.1145/3842793.3842813
Metadata
- Authors
- Shen, Y., Ding, N., Zheng, H.-T., Li, Y., & Yang, M.
- Affiliations
- Sun Yat-sen University (CN)
- Tsinghua Shenzhen International Graduate School (CN)
- Chinese Academy of Sciences (CN)
- Venue
- IEEE Transactions on Knowledge and Data Engineering
- Published
- 2021-11-01
- Volume
- 33
- Issue
- 11
- Pages
- 3607-3617
- ISSN
- 1041-4347 (ISSN-L)
- 1558-2191
- 2326-3865
- OpenAlex
- W3003507729
- Cited by
- 153
- References
- 57
- Citations by year
- 2026: 9 · 2025: 20 · 2024: 31 · 2023: 74 · 2022: 13 · 2021: 6
- FWCI
- 9.14
- Type
- journal article
- Language
- en
- Open access
- closed
- Licence
- Locations
- IEEE Transactions on Knowledge and Data Engineering (publishedVersion)
- Funders
- National Natural Science Foundation of China (61602013, 61773229)
- Shenzhen Fundamental Research Program (JCYJ20170818091546869)
- Basic Scientific Research Program of Shenzhen City (JCYJ20160331184440545)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Advanced Graph Neural Networks
- Physical Sciences › Computer Science › Artificial Intelligence › Topic Modeling
- Physical Sciences › Computer Science › Artificial Intelligence › Semantic Web and Ontologies
- Keywords
- knowledge graph completion, path reasoning, entity types, link prediction, entity prediction, knowledge graph incompleteness, entity representation learning
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.