Research on Knowledge Graph Completion Based on Paired Relation Vectors Convolution

doi:10.3778/j.issn.1673-9418.2501037

Abstract

Abstract: Knowledge graph completion aims to solve the incompleteness problem of the knowledge graph by inferring the missing triples based on the triples already known in the knowledge graph. Most of the existing methods directly fuse entities and relations to extract features, ignoring the common features and specific attributes between the triples. To this end, this paper proposes ConvPair, a convolutional neural network model based on pairwise relation vectors, to improve the link prediction performance of knowledge graph completion through pairwise relation modelling, feature fusion optimization, and relation-aware convolutional operations. The key idea of the ConvPair model is to split the relation r into a head relation rh and a tail relation rt, and rh is fused with the head entity h, and then a commonality feature encoding module is applied to obtaining the common feature entity f. Next, f is fused with rt to predict the tail entity t through the specific attribute extraction module. In terms of entity-relationship fusion, a checkerboard reshaping operation is performed on the vector representations of h and rh to fully fuse the features; at the same time, the vector representations of f and rt are directly spliced together, preserving the ternary translation property in the specific attribute extraction. Finally, a relation-aware convolutional kernel is designed to effectively handle complex relations and extract relation-specific features. Experimental results show that ConvPair outperforms existing state-of-the-art models on datasets such as FB15k-237, WN18RR and YAGO3-10, demonstrating excellent performance and generalizability.

Key words: knowledge graph completion, paired relation vectors, convolutional neural network, link prediction

摘要： 知识图谱补全旨在依据知识图谱中已知三元组推理出缺失的三元组，以解决知识图谱的不完整性问题。现有方法大多将实体和关系直接融合提取特征，忽略了三元组中之间的共性特征和具体属性。为此，提出了一种基于成对关系向量的卷积神经网络模型ConvPair，通过成对关系建模、特征融合优化和关系感知卷积操作，提升知识图谱补全的链接预测性能。ConvPair模型的核心思想是将关系r拆分为头关系rh和尾关系rt，rh与头实体h融合后，通过共性特征编码模块得到共性特征实体f。接着，f与rt进行融合，通过具体属性提取模块来预测尾实体t。在实体与关系的融合方面，对h和rh的向量表示进行棋盘重塑操作，以充分融合特征；同时，直接拼接f和rt的向量表示，保留在提取具体属性时的三元组翻译特性。最后，设计关系感知卷积核，有效处理了复杂关系并提取关系的特定特征。实验结果表明，ConvPair在FB15k-237、WN18RR、YAGO3-10等数据集上优于现有先进模型，展现了卓越的性能和泛化能力。

关键词: 知识图谱补全, 成对关系向量, 卷积神经网络, 链接预测

ZHANG Yuchen, ZHU Xiaoxu, LI Peifeng. Research on Knowledge Graph Completion Based on Paired Relation Vectors Convolution[J]. Journal of Frontiers of Computer Science and Technology, 2025, 19(10): 2782-2792.

张宇晨, 朱晓旭, 李培峰. 基于成对关系向量卷积的知识图谱补全研究[J]. 计算机科学与探索, 2025, 19(10): 2782-2792.

References

[1] 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: ACM, 2008: 1247-1250.
[2] MILLER G A. WordNet[J]. Communications of the ACM, 1995, 38(11): 39-41.
[3] 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: ACM, 2007: 697-706.
[4] MOTTIN D, LISSANDRINI M, VELEGRAKIS Y, et al. Exemplar queries: a new way of searching[J]. The VLDB Journal, 2016, 25(6): 741-765.
[5] HAO Y C, ZHANG Y Z, LIU K, et al. An end-to-end model for question answering over knowledge base with cross-attention combining global knowledge[C]//Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics. Stroudsburg: ACL, 2017: 221-231.
[6] GUO Q Y, ZHUANG F Z, QIN C, et al. A survey on know-ledge graph-based recommender systems[J]. IEEE Transactions on Knowledge and Data Engineering, 2020, 34(8):3549-3568.
[7] BORDES A, USUNIER N, GARCIA-DURAN A, et al. Translating embeddings for modeling multi-relational data[C]//Proceedings of the 27th International Conference on Neural Information Processing Systems, 2013: 2787-2795.
[8] NICKEL M, TRESP V, KRIEGEL H P. A three-way model for collective learning on multi-relational data[C]//Proceedings of the 28th International Conference on Machine Learning, 2011: 809-816.
[9] DETTMERS T, MINERVINI P, STENETORP P, et al. Convolutional 2D knowledge graph embeddings[J]. Proceedings of the AAAI Conference on Artificial Intelligence, 2018, 32(1): 1811-1818.
[10] VASHISHTH S, SANYAL S, NITIN V, et al. InteractE: improving convolution-based knowledge graph embeddings by increasing feature interactions[J]. Proceedings of the AAAI Conference on Artificial Intelligence, 2020, 34(3): 3009-3016.
[11] SHANG B, ZHAO Y L, LIU J, et al. LAFA: multimodal knowledge graph completion with link aware fusion and aggregation[J]. Proceedings of the AAAI Conference on Artificial Intelligence, 2024, 38(8): 8957-8965.
[12] WANG Z, ZHANG J W, FENG J L, et al. Knowledge graph embedding by translating on hyperplanes[J]. Proceedings of the AAAI Conference on Artificial Intelligence, 2014, 28(1): 1112-1119.
[13] LIN Y K, LIU Z Y, SUN M S, et al. Learning entity and relation embeddings for knowledge graph completion[J]. Proceedings of the AAAI Conference on Artificial Intelligence, 2015, 29(1): 2181-2187.
[14] JI G L, HE S Z, XU L H, et al. Knowledge graph embedding via dynamic mapping matrix[C]//Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing. Stroudsburg: ACL, 2015: 687-696.
[15] FAN M, ZHOU Q, CHANG E, et al. Transition-based knowledge graph embedding with relational mapping properties[C]//Proceedings of the 28th Pacific Asia Conference on Language, Information and Computation, 2014: 328-337.
[16] CHAO L L, HE J S, WANG T F, et al. PairRE: knowledge graph embeddings via paired relation vectors[C]//Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing. Stroudsburg: ACL, 2021: 4360-4369.
[17] FANG Y, LU W, LIU X D, et al. CircularE: a complex space circular correlation relational model for link prediction in knowledge graph embedding[J]. IEEE/ACM Transactions on Audio, Speech, and Language Processing, 2023, 31: 3162-3175.
[18] JIN L, YAO Z, CHEN M Y, et al. A comprehensive study on knowledge graph embedding over relational patterns based on rule learning[C]//Proceedings of the 22nd International Semantic Web Conference. Cham: Springer, 2023: 290-308.
[19] YANG B S, YIH W T, HE X D, et al. Embedding entities and relations for learning and inference in knowledge bases[C]//Proceedings of the 2nd International Conference on Learning Representations, 2014.
[20] TROUILLON T, WELBL J, RIEDEL S, et al. Complex embeddings for simple link prediction[C]//Proceedings of the 33rd International Conference on International Conference on Machine Learning, 2016: 2071-2080.
[21] NICKEL M, ROSASCO L, POGGIO T. Holographic embeddings of knowledge graphs[J]. Proceedings of the AAAI Conference on Artificial Intelligence, 2016, 30(1): 1955-1961.
[22] KAZEMI S M, POOLE D. Simple embedding for link prediction in knowledge graphs[C]//Advances in Neural Information Processing Systems 31, 2018: 4289-4300.
[23] ZHANG W, PAUDEL B, ZHANG W, et al. Interaction embeddings for prediction and explanation in knowledge graphs[C]//Proceedings of the 12th ACM International Conference on Web Search and Data Mining. New York: ACM, 2019: 96-104.
[24] XU W T, ZHENG S, HE L, et al. SEEK: segmented embedding of knowledge graphs[C]//Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics. Stroudsburg: ACL, 2020: 3888-3897.
[25] NGUYEN D Q, NGUYEN T D, NGUYEN D Q, et al. A novel embedding model for knowledge base completion based on convolutional neural network[C]//Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. Stroudsburg: ACL, 2018: 327-333.
[26] JIANG X T, WANG Q, WANG B. Adaptive convolution for multi-relational learning[C]//Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. Stroudsburg: ACL, 2019: 978-987.
[27] BALA?EVI? I, ALLEN C, HOSPEDALES T M. Hypernetwork knowledge graph embeddings[C]//Proceedings of the 28th International Conference on Artificial Neural Networks. Cham: Springer, 2019: 553-565.
[28] ZHOU Z H, WANG C, FENG Y, et al. JointE: jointly utilizing 1D and 2D convolution for knowledge graph embedding[J]. Knowledge-Based Systems, 2022, 240: 108100.
[29] SCHLICHTKRULL M, KIPF T N, BLOEM P, et al. Modeling relational data with graph convolutional networks[C]//The Semantic Web: 15th International Conference. Cham: Springer, 2018: 593-607.
[30] SHANG C, TANG Y, HUANG J, et al. End-to-end structure-aware convolutional networks for knowledge base completion[J]. Proceedings of the AAAI Conference on Artificial Intelligence, 2019, 33(1): 3060-3067.
[31] LIU W J, REN Z J, CHEN L. Knowledge reasoning based on graph neural networks with multi-layer top-p message passing and sparse negative sampling[J]. Knowledge-Based Systems, 2025, 311: 113063.
[32] LIU W, WANG Z. Event relation extraction based on heterogeneous graph attention networks and event ontology direction induction[J]. Tsinghua Science and Technology, 2024. DOI: 10.26599/TST.2024.9010104.
[33] ZHANG Z L, LI Z F, LIU H, et al. Multi-scale dynamic convolutional network for knowledge graph embedding[J]. IEEE Transactions on Knowledge and Data Engineering, 2022, 34(5): 2335-2347.
[34] WANG C X, WANG X, LI Z, et al. HyConvE: a novel embedding model for knowledge hypergraph link prediction with convolutional neural networks[C]//Proceedings of the ACM Web Conference 2023. New York: ACM, 2023: 188-198.
[35] LI Z, WANG C X, WANG X, et al. HJE: joint convolutional representation learning for knowledge hypergraph completion[J]. IEEE Transactions on Knowledge and Data Engineering, 2024, 36(8): 3879-3892.
[36] FENG J Z, WEI Q K, CUI J M, et al. Novel translation knowledge graph completion model based on 2D convolution[J]. Applied Intelligence, 2022, 52(3): 3266-3275.
[37] JIANG D, WANG R G, XUE L X, et al. Multisource hierarchical neural network for knowledge graph embedding[J]. Expert Systems with Applications, 2024, 237: 121446.
[38] LIN X V, SOCHER R, XIONG C M. Multi-hop knowledge graph reasoning with reward shaping[C]//Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing. Stroudsburg: ACL, 2018: 3243-3253.