Abstract Knowledge graph reasoning is an essential approach to address the incompleteness of knowledge graphs. The existing embedding-based reasoning models rely on accurate facts and suffer from poor interpretability. Rule-based reasoning models depend on the completeness of knowledge graphs, resulting in low inference performance on sparse data and an inability to express inference patterns accurately. To address these issues, a model of knowledge graph reasoning combining rule inference patterns and fact embedding(RPFE) is proposed. First, BoxE is employed as the base embedding model to achieve the embedding representation of facts. Second, the inference pattern diversity functions are designed to assist the embedding models in capturing the rules of different inference patterns, providing intuitive embedded interpretation for rule learning. Then, the fact distance consistency scoring functions are proposed to enhance the embedding representation. Finally, the rules and fact scores are optimized to compensate the lack of high-quality facts in knowledge graphs and improve the interpretability of the reasoning. Experiments on three public datasets indicate that the RPFE yields excellent performance in knowledge graph reasoning.
Fund:National Key Research and Development Program of China(No.2023YFC3304900), Applied Basic Research Program of Liaoning Province(No.2022JH2/101300250), University-Industry Collaborative Education Program of Ministry of Edu-cation of China(No.230701160261310), the General Program of University Basic Scientific Research of Education Department of Liaoning Province(Science and Engineering)(Initiating Flagship Service for Local Projects)(No.JYTMS20230761), Doctoral Startup Project of Natural Science Foundation of Liaoning Province(No.2023-BS-085)
Corresponding Authors:
SONG Baoyan, Ph.D., professor. Her research interests include database techniques and big data ma-nagement.
About author:: SHAN Xiaohuan, Ph.D., experimentalist. Her research interests include graph data processing technology and knowledge graph data management. JIANG Jiantao, Master student. His research interests include knowledge graph data management. CHEN Ze, Ph.D. candidate. His research interests include natural language processing and knowledge graph data management.
[1] JI S X, PAN S R, CAMBRIA E, et al. A Survey on Knowledge Graphs: Representation, Acquisition, and Applications. IEEE Tran-sactions on Neural Networks and Learning Systems, 2022, 33(2): 494-514. [2] TIAN L, ZHOU X, WU Y P, et al. Knowledge Graph and Know-ledge Reasoning: A Systematic Review. Journal of Electronic Science and Technology, 2022, 20(2). DOI: 10.1016/j.jnlest.2022.100159. [3] LI D Z, QU H B, WANG J Q.A Survey on Knowledge Graph-Based Recommender Systems // Proc of the China Automation Congress. Washington, USA: IEEE, 2023: 2925-2930. [4] 乔凯,陈可佳,陈景强.基于知识图谱与关键词注意机制的中文医疗问答匹配方法.模式识别与人工智能, 2021, 34(8): 733-741. (QIAO K, CHEN K J, CHEN J Q.Chinese Medical Question Answering Matching Method Based on Knowledge Graph and Keyword Attention Mechanism. Pattern Recognition and Artificial Intelligence, 2021, 34(8): 733-741.) [5] CHENG K W, YANG Z Q, ZHANG M, et al. UniKER: A Unified Framework for Combining Embedding and Definite Horn Rule Reasoning for Knowledge Graph Inference // Proc of the Conference on Empirical Methods in Natural Language Processing. Stroudsburg, USA: ACL, 2021: 9753-9771. [6] LEE J, CHUNG C, WHANG J J.InGram: Inductive Knowledge Graph Embedding via Relation Graphs. Journal of Machine Learning Research, 2023, 202: 18796-18809. [7] 李凤英,何晓蝶,董荣胜.融合语义信息的知识图谱多跳推理模型.模式识别与人工智能, 2022, 35(11): 1025-1032. (LI F Y, HE X D, DONG R S.Multi-hop Inference Model for Knowledge Graphs Incorporating Semantic Information. Pattern Re-cognition and Artificial Intelligence, 2022, 35(11): 1025-1032.) [8] CHENG K W, LIU J H, WANG W, et al. RLogic: Recursive Logical Rule Learning from Knowledge Graphs // Proc of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining. New York, USA: ACM, 2022: 179-189. [9] GUO S, LI L, HUI Z, et al. Knowledge Graph Embedding Preserving Soft Logical Regularity // Proc of the 29th ACM International Conference on Information and Knowledge Management. New York, USA: ACM, 2020: 425-434. [10] ZHANG W, PAUDEL B, WANG L, et al. Iteratively Learning Embeddings and Rules for Knowledge Graph Reasoning // Proc of the 28th World Wide Web Conference. New York, USA: ACM, 2019: 2366-2377. [11] CHEN S Y, CAI Y F, FANG H, et al. Differentiable Neuro-Symbolic Reasoning on Large-Scale Knowledge Graphs // Proc of the 37th International Conference on Neural Information Processing Sys-tems. Cambridge, USA: MIT Press, 2024: 28139-28154. [12] GUO S, WANG Q, WANG L H, et al. Jointly Embedding Know-ledge Graphs and Logical Rules // Proc of the Conference on Empirical Methods in Natural Language Processing. Stroudsburg, USA: ACL, 2016: 192-202. [13] GUO S, WANG Q, WANG L H, et al. Knowledge Graph Embe-dding with Iterative Guidance from Soft Rules. Proceeding of the AAAI Conference on Artificial Intelligence, 2018, 32(1): 4816-4823. [14] TANG X J, ZHU S C, LIANG Y T, et al. RulE: Knowledge Graph Reasoning with Rule Embedding // KU L W, MARTINS A, SRIKUMAR V, eds. Findings of the Association for Computational Linguistics. Stroudsburg, USA: ACL, 2024: 4316-4335. [15] BORDES A, USUNIER N, GARCIA-DURÁN AQ, et al. Translating Embeddings for Modeling Multi-relational Data // Proc of the 26th International Conference on Neural Information Processing Systems. Cambridge, USA: MIT Press, 2013, II: 2787-2795. [16] SUN Z Q, DENG Z H, NIE J Y, et al. RotatE: Knowledge Graph Embedding by Relational Rotation in Complex Space[C/OL].[2024-07-23]. https://arxiv.org/pdf/1902.10197. [17] ZHANG Q J, XU Y D.Knowledge Graph Embedding with Inverse Function Representation for Link Prediction. Engineering Applications of Artificial Intelligence, 2024, 127(A). DOI: 10.1016/J.ENGAPPAI.2023.107225. [18] TROUILLON T, WELBL J, RIEDEL S, et al. Complex Embe-ddings for Simple Link Prediction // Proc of the 33rd International Conference on Machine Learning. New York, USA: ACM, 2016: 2071-2080. [19] CAO Z S, XU Q Q, YANG Z Y, et al. Geometry Interaction Knowledge Graph Embeddings. Proceedings of the AAAI Confe-rence on Artificial Intelligence, 2022, 36(5): 5521-5529. [20] WANG Y Z, WANG H Z, LU W B, et al. HyGGE: Hyperbolic Graph Attention Network for Reasoning over Knowledge Graphs. Information Sciences, 2023, 630: 190-205. [21] REN H Y, HU W H, LESKOVEC J.QUERY2BOX: Reasoning over Knowledge Graphs in Vector Space Using Box Embeddings[C/OL]. [2024-07-23].https://arxiv.org/pdf/2002.05969. [22] ABBOUD R, CEYLAN I I, LUKASIEWICZ T, et al. BoxE: A Box Embedding Model for Knowledge Base Completion // Proc of the 34th International Conference on Neural Information Processing Systems. Cambridge, USA: MIT Press, 2020: 9649-9661. [23] LI W D, PENG R, LI Z.Improving Knowledge Graph Completion via Increasing Embedding Interactions. Applied Intelligence, 2022, 52(8): 9289-9307. [24] LAN Y Y, HE S Z, LIU K, et al. Knowledge Reasoning via Jointly Modeling Knowledge Graphs and Soft Rules. Applied Sciences, 2023, 13(19). DOI: 10.3390/APP131910660. [25] QU M, CHEN J K, XHONNEUX L P, et al. RNNLogic: Learning Logic Rules for Reasoning on Knowledge Graphs[C/OL]. [2024-07-23]. http://arxiv.org/pdf/201004029. [26] HE T, LIU M, CAO Y X, et al. VEM2L: An Easy but Effective Framework for Fusing Text and Structure Knowledge on Sparse Knowledge Graph Completion. Data Mining and Knowledge Discovery, 2024, 38(2): 343-371.
2024, Vol. 37 
