Knowledge Graph Completion Integrating Relational Context Semantics

doi:10.19678/j.issn.1000-3428.0070677

Abstract

Abstract:

Existing Knowledge Graph Completion (KGC) methods fail to effectively distinguish semantic differences among paths at different levels and cannot dynamically adjust relation representations by fully leveraging neighborhood context information. Consequently, contextual semantics remain insufficiently understood. To address these issues, this paper proposes a KGC model integrating relational context semantics, named RCSKGC, for enhancing the semantic representation of learned paths and neighborhood information. First, the local and global encoding of multi-hop paths at different levels is performed using a Bidirectional Gated Recurrent Unit (Bi-GRU) and an attention mechanism to extract effective path information. Meanwhile, the fine-grained semantic features of the path information at different levels are further enhanced through relational embedding contrastive learning. Second, a dual-attention mechanism and dynamic weighting strategy are employed to capture the neighborhood-level information of relations and learn their semantics through a "neighborhood—entity—relation" approach. Finally, the two types of relational representations are aggregated and used as inputs for the decoder to perform KGC. The results of experiments on the FB15k-237 dataset demonstrate that, compared to the best results of the baseline methods, RCSKGC achieves improvements of 1.4, 0.8, 1.3, and 2.1 percentage points in the Mean Reciprocal Rank (MRR), Hits@1, Hits@3, and Hits@10, respectively. Further, on the WN18RR dataset, RCSKGC shows improvements of 0.8 and 1.0 percentage points in MRR and Hits@3, respectively. These results validate the effectiveness of the proposed method.

Key words: Knowledge Graph Completion(KGC), contrastive learning, attention mechanism, semantic, Bidirectional Gate Recurrent Unit (Bi-GRU)

摘要：

现有知识图谱补全(KGC)方法未能有效区分不同层级路径的语义差异, 且关系表示未能充分利用邻域上下文信息进行动态调整, 导致对上下文语义的理解不够全面。针对以上问题, 提出一种融合关系上下文语义的知识图谱补全模型RCSKGC, 旨在增强学习路径和邻域信息的语义表达。首先, 通过双向门控循环单元(Bi-GRU)和注意力机制, 针对不同层级的多跳路径进行局部和全局编码, 从而提取有效路径信息, 同时, 通过关系嵌入对比学习进一步增强不同层级路径信息的细粒度语义特征; 其次, 采用双重注意力机制和动态加权策略捕捉关系的邻域层级信息, 通过"邻域-实体-关系"的方式学习关系的语义; 最后, 聚合两种关系表示, 并将其作为解码器的输入以完成KGC。实验结果表明: 在FB15k-237数据集上, 相较于基线方法的最优结果, RCSKGC的平均倒数排名(MRR)、Hits@1、Hits@3和Hits@10分别提升1.4、0.8、1.3和2.1百分点; 在WN18RR数据集上, 与基线方法的最优结果相比, RCSKGC的MRR、Hits@3分别提升0.8、1.0百分点, 验证了所提方法的有效性。

关键词: 知识图谱补全, 对比学习, 注意力机制, 语义, 双向门控循环单元

ZHAI Sheping, MA Mengyao, ZHANG Wenjing, YANG Rui. Knowledge Graph Completion Integrating Relational Context Semantics[J]. Computer Engineering, 2026, 52(9): 113-122.

翟社平, 马梦瑶, 张文静, 杨锐. 融合关系上下文语义的知识图谱补全[J]. 计算机工程, 2026, 52(9): 113-122.

/ Recommend / Download Citations

URL: https://www.ecice06.com/EN/10.19678/j.issn.1000-3428.0070677

https://www.ecice06.com/EN/Y2026/V52/I9/113

Figures/Tables 10

Fig.1 Overall framework of RCSKGC model

Fig.2 The impact of embedding dimension d on FB15k-237

Fig.3 The impact of embedding dimension d on WN18RR

Fig.4 The impact of contrastive learning settings on FB15k-237

Fig.5 The impact of contrastive learning settings on WN18RR

Fig.6 The impact of similarity threshold s on FB15k-237

Fig.7 The impact of similarity threshold s on WN18RR

References 27

1	马恒志, 钱育蓉, 冷洪勇, 等. 知识图谱嵌入研究进展综述. 计算机工程, 2025, 51 (2): 18- 34. doi: 10.19678/j.issn.1000-3428.0068386
	MA H Z , QIAN Y R , LENG H Y , et al. Review of research progress on knowledge graph embedding. Computer Engineering, 2025, 51 (2): 18- 34. doi: 10.19678/j.issn.1000-3428.0068386
2	AUER S, BIZER C, KOBILAROV G, et al. DBpedia: a nucleus for a web of open data[EB/OL]. [2024-10-05]. https://link.springer.com/chapter/10.1007/978-3-540-76298-0_52.
3	BOLLACKER K, EVANS C, PARITOSH P, et al. Freebase: a collaboratively created graph database for structuring human knowledge[C]//Proceedings of the 2008 ACM SIGMOD International Conference on Management of Data. New York, USA: ACM Press, 2008: 1247-1250.
4	SUCHANEK F M, KASNECI G, WEIKUM G. YAGO: a core of semantic knowledge[C]//Proceedings of the 16th International Conference on World Wide Web. New York, USA: ACM Press, 2007: 697-706.
5	张文豪, 徐贞顺, 刘纳, 等. 知识图谱补全方法研究综述. 计算机工程与应用, 2024, 60 (12): 61- 73.
	ZHANG W H , XU Z S , LIU N , et al. Overview of knowledge graph completion methods. Computer Engineering and Applications, 2024, 60 (12): 61- 73.
6	BORDES A, USUNIER N, GARCA D A, et al. Translating embeddings for modeling multi-relational data[EB/OL]. [2024-10-05]. https://papers.nips.cc/paper/2013/file/1cecc7a77928ca8133fa24680a88d2f9-Paper.pdf.
7	WANG Z , ZHANG J W , FENG J L , et al. Knowledge graph embedding by translating on hyperplanes. Proceedings of the AAAI Conference on Artificial Intelligence, 2014, 28 (1): 1112- 1119.
8	LIN Y K , LIU Z Y , SUN M S , et al. Learning entity and relation embeddings for knowledge graph completion. Proceedings of the AAAI Conference on Artificial Intelligence, 2015, 29 (1): 2181- 2187.
9	LI J, SU X D, ZHANG F J, et al. TransERR: translation-based knowledge graph embedding via efficient relation rotation[C]//Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024). [S. l. ]: ACL, 2024: 16727-16737.
10	NICKEL M, TRESP V, KRIEGEL H P. A three-way model for collective learning on multi-relational data[EB/OL]. [2024-10-05]. https://icml.cc/2011/papers/438_icmlpaper.pdf.
11	YANG B S, YIH W T, HE X D, et al. Embedding entities and relations for learning and inference in knowledge bases[EB/OL]. [2024-10-05]. https://arxiv.org/abs/1412.6575.
12	TROUILLON T, WELBL J, RIEDEL S, et al. Complex embeddings for simple link prediction[EB/OL]. [2024-10-05]. https://arxiv.org/abs/1606.06357.
13	BALAŽEVI AC'G I, ALLEN C, HOSPEDALES T M. TuckER: tensor factorization for knowledge graph completion[EB/OL]. [2024-10-05]. https://arxiv.org/abs/1901.09590.
14	DETTMERS T, MINERVINI P, STENETORP P, et al. Convolutional 2D knowledge graph embeddings[EB/OL]. [2024-10-05]. https://arxiv.org/abs/1707.01476.
15	SHANG C , TANG Y , HUANG J , et al. End-to-end structure-aware convolutional networks for knowledge base completion. Proceedings of the AAAI Conference on Artificial Intelligence, 2019, 33 (1): 3060- 3067. doi: 10.1609/aaai.v33i01.33013060
16	SUN X C , CHEN Q , HAO M X , et al. MConvKGC: a novel multi-channel convolutional model for knowledge graph completion. Computing, 2024, 106 (3): 915- 937. doi: 10.1007/s00607-023-01247-w
17	HUANG J , LU T , ZHU J , et al. Multi-relational knowledge graph completion method with local information fusion. Applied Intelligence, 2022, 52 (7): 7985- 7994. doi: 10.1007/s10489-021-02876-4
18	马坤, 安敬民, 李冠宇. 动态聚合实体和关系上下文的知识图谱补全. 计算机工程, 2023, 49 (8): 77-84, 95. doi: 10.19678/j.issn.1000-3428.0065410
	MA K , AN J M , LI G Y . Knowledge graph completion with dynamically aggregating context of entity and relation. Computer Engineering, 2023, 49 (8): 77-84, 95. doi: 10.19678/j.issn.1000-3428.0065410
19	LIN Y K, LIU Z Y, LUAN H B, et al. Modeling relation paths for representation learning of knowledge bases[C]//Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing. [S. l. ]: ACL, 2015: 705-714.
20	ZHU Q N , ZHOU X F , TAN J L , et al. Knowledge base reasoning with convolutional-based recurrent neural networks. IEEE Transactions on Knowledge and Data Engineering, 2021, 33 (5): 2015- 2028.
21	WANG H , SONG D D , WU Z J , et al. A collaborative learning framework for knowledge graph embedding and reasoning. Knowledge-Based Systems, 2024, 289, 111505. doi: 10.1016/j.knosys.2024.111505
22	YIN H , ZHONG J , LI R Z , et al. High-order neighbors aware representation learning for knowledge graph completion. IEEE Transactions on Neural Networks and Learning Systems, 2025, 36 (3): 5273- 5287. doi: 10.1109/TNNLS.2024.3383873
23	ZHANG X , ZHANG C X , GUO J T , et al. Graph attention network with dynamic representation of relations for knowledge graph completion. Expert Systems with Applications, 2023, 219, 119616. doi: 10.1016/j.eswa.2023.119616
24	PEI S C, KOU Z Y, ZHANG Q N, et al. Few-shot low-resource knowledge graph completion with multi-view task representation generation[C]//Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining. New York, USA: ACM Press, 2023: 1862-1871.
25	YIN H , ZHONG J , LI R Z , et al. Disentangled relational graph neural network with contrastive learning for knowledge graph completion. Knowledge-Based Systems, 2024, 295, 111828. doi: 10.1016/j.knosys.2024.111828
26	XIANG Y , HE H G , YU Z T , et al. Concept-driven representation learning model for knowledge graph completion. Expert Systems with Applications, 2025, 268, 126297. doi: 10.1016/j.eswa.2024.126297
27	LI D A , MIAO S Y , ZHAO B F , et al. ConvHiA: convolutional network with hierarchical attention for knowledge graph multi-hop reasoning. International Journal of Machine Learning and Cybernetics, 2023, 14 (7): 2301- 2315. doi: 10.1007/s13042-022-01764-8

[1]	LIU Junping, WANG Runpeng, HU Xinrong, PENG Tao, WANG Bangchao, YANG Huali, ZHU Qiang. Research on Entity Linking Method Based on Contrastive Learning and Re-ranking [J]. Computer Engineering, 2026, 52(9): 123-132.
[2]	YUAN Lining, FENG Wengang, LIU Zhao. Academic Paper Classification Method Based on Improved Graph Convolutional Network [J]. Computer Engineering, 2026, 52(9): 154-164.
[3]	LI Yamin, XIANG Wen, CHAI Li, XIANG Yao. Dual-Stage Low-Light Image Enhancement Network Based on HVI Color Space Transformer [J]. Computer Engineering, 2026, 52(9): 228-241.
[4]	YANG Li, CHEN Yanping, HUANG Hui, HUANG Ruizhang, QIN Yongbin. A Named Entity Recognition Method Based on Semantic Plane Interpolation [J]. Computer Engineering, 2026, 52(9): 92-101.
[5]	LI Danbo, YAN Xuexiong, MAO Enhui. Research and Testing on Semantic Inconsistency of HTTP [J]. Computer Engineering, 2026, 52(9): 293-305.
[6]	HAN Yanling, ZHU Xiaojun, WANG Jing, PAN Haiyan, ZHANG Yun. Passive Microwave Sea Ice Thickness Inversion Based on SIT-TransNET [J]. Computer Engineering, 2026, 52(8): 390-399.
[7]	ZHAO Tao, DONG Lihong, QIN Yi. Underground Personnel Detection Algorithm Combining Attention and Lightweight Network [J]. Computer Engineering, 2026, 52(8): 400-411.
[8]	ZHENG Yuhao, LI Jianhua. Initial Phase Training Method of Class Incremental Learning Based on Class Boundary Sample Generation and Fine-Tuning [J]. Computer Engineering, 2026, 52(7): 86-93.
[9]	JIN Jing, HU Chudi, CHEN Gang. Medical Image Segmentation Method Based on Multi-Scale Self-Attention Transformer [J]. Computer Engineering, 2026, 52(7): 199-209.
[10]	DANG Weichao, PEI Lixian, GAO Gaimei, LIU Chunxia. Weakly-Supervised Temporal Action Localization via Video—Text Semantic Alignment and Full Video Dependency [J]. Computer Engineering, 2026, 52(7): 354-367.
[11]	LI Zhongwei, LI Keyi, LIU Xin. Sequential Recommendation Algorithm Based on Data Augmentation and Integrated Self-Attention [J]. Computer Engineering, 2026, 52(7): 94-106.
[12]	LI Jinru, PAN Qingxian, GAO Zhaolong, WEI Kai, FAN Zequn. Crowdsourcing Task Recommendation Method Based on Collaborative Knowledge Graph and Hybrid Neural Network [J]. Computer Engineering, 2026, 52(7): 155-167.
[13]	LIANG Ziyi, WANG Zihao, LIU Tianquan, LI Liping, ZHU Yuanfei, LU Cunyue. PASRGAN: A Super-Resolution Pathological Image Generation Algorithm Based on Parallel Attention Mechanism [J]. Computer Engineering, 2026, 52(7): 189-198.
[14]	WU Di, ZHANG Le, CHEN Yao. Cross-Behavior Feature Regularization and Interaction Contrastive Learning Based Multi-Behavior Recommendation [J]. Computer Engineering, 2026, 52(7): 143-154.
[15]	HE Mingyan, LI Siyuan, LIU Peng, HUANG Jianhua. Opponent Modeling Based on Cross-Attention Diffusion Model [J]. Computer Engineering, 2026, 52(7): 76-85.

Please choose a citation manager

Content to export