Aggregating Global Interaction and Local Interaction for Knowledge Graph Completion

doi:10.3778/j.issn.1673-9418.2409029

Abstract

Abstract: Knowledge graphs suffer from incompleteness, largely determining the application and development of downstream tasks. Therefore, it is necessary to improve the knowledge graphs to supplement the missed values, i.e., knowledge graph completion. Many existing knowledge graph completion models reshape entity and relation embeddings to capture the local interaction. However, such a method corrupts the original triplet structure and can only utilize the local interaction while ignoring the impact of global interaction between entities and relations. Therefore, a knowledge graph completion method called AGILI, which aggregates global interaction and local interaction, is proposed. This method introduces a self-attention mechanism to evaluate the information correlation degree between head entities and relations, and then generates embedding representations that incorporate global interaction information. Then, it employs a convolutional neural network to capture local interaction information from the embedding representations. In addition, a learnable interaction aggregator based on relationship weights is designed. When the two types of interactions are fused, their importance can be adaptively adjusted according to the relationship category, which improves the expressive ability of the method on multi-relational knowledge graphs. Experimental verification is carried out on the publicly available FB15k-237, WN18RR, and Kinship datasets by link prediction task. Experimental results show that compared with the latest convolutional neural network-based model ConvD, the Hits@1 and Hits@3 metrics of the proposed method are increased by 6.9% and 5.3% respectively on the FB15k-237 dataset, demonstrating the superiority of the proposed method.

Key words: knowledge graph, knowledge graph completion, link prediction, self-attention mechanism, convolutional neural network

摘要： 知识图谱的不完整性严重影响了下游任务的应用与发展，因此，有必要对其进行改进以补充缺失值，即知识图谱补全。现有的知识图谱补全模型大多重组实体关系嵌入表示以捕获局部交互。但这种方法破坏了三元组的原有结构，只能利用单一的局部交互而忽略了实体关系间全局交互的影响。为此，提出一种聚合全局交互与局部交互的知识图谱补全方法AGILI。该方法首先引入自注意力机制获取头实体和关系间的信息关联程度，生成融入全局交互信息的嵌入表示，再采用卷积神经网络从新嵌入表示中提取局部交互信息，设计基于关系权重的可学习交互聚合器，在将全局交互与局部交互进行特征融合时，可以根据关系类别自适应地调整两种交互的重要程度，提高方法在多关系知识图谱上的表达能力。在公开数据集FB15k-237、WN18RR和Kinship上通过链接预测任务进行实验验证，实验结果表明，与最新的基于卷积神经网络的模型ConvD相比，所提出的方法在FB15k-237数据集上Hits@1、Hits@3指标分别提高了6.9%、5.3%，证明了所提出方法的优越性。

关键词: 知识图谱, 知识图谱补全, 链接预测, 自注意力机制, 卷积神经网络

FENG Yong, LUAN Chaojie, WANG Rongbing, XU Hongyan, ZHANG Yonggang. Aggregating Global Interaction and Local Interaction for Knowledge Graph Completion[J]. Journal of Frontiers of Computer Science and Technology, 2025, 19(7): 1909-1917.

冯勇, 栾超杰, 王嵘冰, 徐红艳, 张永刚. 聚合全局交互与局部交互的知识图谱补全[J]. 计算机科学与探索, 2025, 19(7): 1909-1917.

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] VRANDE?I? D, KR?TZSCH M. Wikidata[J]. Communications of the ACM, 2014, 57(10): 78-85.
[3] 毛存礼, 郝鹏鹏, 雷雄丽, 等. 基于实体语义扩展的跨境民族文化文本检索[J]. 中文信息学报, 2022, 36(11): 101-109.
MAO C L, HAO P P, LEI X L, et al. Entity semantic extension based culture text retrieval for cross-country ethnic group[J]. Journal of Chinese Information Processing, 2022, 36(11): 101-109.
[4] 张鹤译, 王鑫, 韩立帆, 等. 大语言模型融合知识图谱的问答系统研究[J]. 计算机科学与探索, 2023, 17(10): 2377-2388.
ZHANG H Y, WANG X, HAN L F, et al. Research on question answering system on joint of knowledge graph and large language models[J]. Journal of Frontiers of Computer Science and Technology, 2023, 17(10): 2377-2388.
[5] 王永贵, 陈书铭, 刘义海, 等. 结合超图对比学习和关系聚类的知识感知推荐算法[J]. 计算机科学与探索, 2024, 18(8): 2140-2155.
WANG Y G, CHEN S M, LIU Y H, et al. Knowledge-aware recommendation algorithm combining hypergraph contrast learning and relational clustering[J]. Journal of Frontiers of Computer Science and Technology, 2024, 18(8): 2140-2155.
[6] 于梦波, 杜建强, 罗计根, 等. 基于知识表示学习的知识图谱补全研究进展[J]. 计算机工程与应用, 2023, 59(18): 59-73.
YU M B, DU J Q, LUO J G, et al. Research progress of knowledge graph completion based on knowledge representation learning[J]. Computer Engineering and Applications, 2023, 59(18): 59-73.
[7] DONG X, GABRILOVICH E, HEITZ G, et al. Knowledge vault: a web-scale approach to probabilistic knowledge fusion[C]//Proceedings of the 20th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. New York: ACM, 2014: 601-610.
[8] WEST R, GABRILOVICH E, MURPHY K, et al. Knowledge base completion via search-based question answering[C]//Proceedings of the 23rd International Conference on World Wide Web. New York: ACM, 2014: 515-526.
[9] 杜雪盈, 刘名威, 沈立炜, 等. 面向链接预测的知识图谱表示学习方法综述[J]. 软件学报, 2024, 35(1): 87-117.
DU X Y, LIU M W, SHEN L W, et al. Survey on representation learning methods of knowledge graph for link prediction[J]. Journal of Software, 2024, 35(1): 87-117.
[10] VASWANI A, SHAZEER N, PARMAR N, et al. Attention is all you need[C]//Advances in Neural Information Processing Systems 30, 2017: 5998-6008.
[11] SI C, YU W, ZHOU P, et al. Inception transformer[C]//Advances in Neural Information Processing Systems 35, 2022: 23495-23509.
[12] LI D, XIA T, WANG J, et al. SDFormer: a shallow-to-deep feature interaction for knowledge graph embedding[J]. Knowledge-Based Systems, 2024, 284: 111253.
[13] CHEN S X, LIU X D, GAO J F, et al. HittER: hierarchical transformers for knowledge graph embeddings[C]//Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing. Stroudsburg: ACL, 2021: 10395-10407.
[14] BAGHERSHAHI P, HOSSEINI R, MORADI H. Self-attention presents low-dimensional knowledge graph embeddings for link prediction[J]. Knowledge-Based Systems, 2023, 260: 110124.
[15] LU F Y, ZHOU J, HUANG X L. Enhancing the convolution-based knowledge graph embeddings by increasing dimension-wise interactions[J]. Data & Knowledge Engineering, 2023, 146: 102184.
[16] BORDES A, USUNIER N, GARCIA-DURAN A, et al. Translating embeddings for modeling multi-relational data[C]//Proceedings of the 26th International Conference on Neural Information Processing Systems, 2013: 2787-2795.
[17] WANG Z, ZHANG J, FENG J, et al. Knowledge graph embedding by translating on hyperplanes[C]//Proceedings of the 28th AAAI Conference on Artificial Intelligence. Palo Alto: AAAI, 2014: 1112-1119.
[18] SUN Z, DENG Z H, NIE J Y, et al. RotatE: knowledge graph embedding by relational rotation in complex space[C]//Proceedings of the 7th International Conference on Learning Representations, 2019: 1-18.
[19] 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.
[20] TROUILLON T, WELBL J, RIEDEL S, et al. Complex embeddings for simple link prediction[C]//Proceedings of the 33rd International Conference on Machine Learning, 2016: 2071-2080.
[21] BALAZEVIC I, ALLEN C, HOSPEDALES T. TuckER: tensor factorization for knowledge graph completion[C]//Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing. Stroudsburg: ACL, 2019: 5184-5193.
[22] TUCKER L R. Some mathematical notes on three-mode factor analysis[J]. Psychometrika, 1966, 31(3): 279-311.
[23] 栗书敬, 黄增峰. 混合曲率空间用于多关系异构知识图谱链接补全[J]. 计算机科学, 2023, 50(4): 172-180.
LI S J, HUANG Z F. Mixed-curve for link completion of multi-relational heterogeneous knowledge graphs[J]. Computer Science, 2023, 50(4): 172-180.
[24] DETTMERS T, MINERVINI P, STENETORP P, et al. Convolutional 2D knowledge graph embeddings[C]//Proceedings of the 32nd AAAI Conference on Artificial Intelligence. Palo Alto: AAAI, 2018: 1811-1818.
[25] VASHISHTH S, SANYAL S, NITIN V, et al. InteractE: improving convolution-based knowledge graph embeddings by increasing feature interactions[C]//Proceedings of the 34th AAAI Conference on Artificial Intelligence. Palo Alto: AAAI, 2020: 3009-3016.
[26] SCHLICHTKRULL M, KIPF T N, BLOEM P, et al. Modeling relational data with graph convolutional networks[C]//Proceedings of the 15th European Semantic Web Conference. Cham: Springer, 2018: 593-607.
[27] VASHISHTH S, SANYAL S, NITIN V, et al. Composition-based multi-relational graph convolutional networks[C]//Proceedings of the 8th International Conference on Learning Representations, 2020: 1-15.
[28] BANSAL T, JUAN D C, RAVI S, et al. A2N: attending to neighbors for knowledge graph inference[C]//Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics. Stroudsburg: ACL, 2019: 4387-4392.
[29] YAO L, MAO C S, LUO Y. KG-BERT: BERT for knowledge graph completion[EB/OL]. [2024-07-23]. https://arxiv.org/abs/1909.03193.
[30] DEVLIN J, CHANG M W, LEE K, et al. BERT: pre-training of deep bidirectional transformers for language understanding [C]//Proceedings of the 17th Annual Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. Stroudsburg: ACL, 2019: 4171-4186.
[31] WANG B, SHEN T, LONG G, et al. Structure-augmented text representation learning for efficient knowledge graph completion[C]//Proceedings of the 30th Web Conference. New York: ACM, 2021: 1737-1748.
[32] 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.
[33] SUN Z Q, VASHISHTH S, SANYAL S, et al. A re-evaluation of knowledge graph completion methods[C]//Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics. Stroudsburg: ACL, 2020: 5516-5522.
[34] LACROIX T, USUNIER N, OBOZINSKI G. Canonical tensor decomposition for knowledge base completion[EB/OL]. [2024-07-23]. https://arxiv.org/abs/1806.07297.
[35] TOUTANOVA K, CHEN D Q. Observed versus latent features for knowledge base and text inference[C]//Proceedings of the 3rd Workshop on Continuous Vector Space Models and Their Compositionality. Stroudsburg: ACL, 2015: 57-66.
[36] KOK S, DOMINGOS P. Statistical predicate invention[C]//Proceedings of the 24th International Conference on Machine Learning, 2007: 433-440.