为了更好地表示邻居节点数量较少的罕见实体,提出基于近邻实体的知识图谱嵌入模型NNKGE,使用K近邻算法获得目标实体的近邻实体作为扩展信息,并在此基础上提出RNNKGE模型,使用改进的K近邻算法获得目标实体在关系上的近邻实体,通过图记忆网络对其编码生成增强的实体表示。通过对公共数据集上实验结果的分析,以上两个模型在仅使用近邻节点的情况下均实现了对基准模型(CoNE)的性能超越,缓解了数据稀疏问题并改善了知识表示性能。
In order to better represent the rare entities with a small number of neighbors, this paper proposes a knowledge graph embedding model based on the nearest neighbors (NNKGE), which uses the K-Nearest Neighbor algorithm to obtain the nearest neighbors of the target entity as extended information. Based on this, the relational nearest neighbors-based knowledge graph embedding model (RNNKGE) is proposed. To generate an enhanced entity representation, the nearest neighbors of the target entity in relation are obtained by the improved K-Nearest Neighbor algorithm and encoded by the graph memory network. Through the analysis of the experimental results on the public datasets, the above two models outperform the benchmark model (CoNE) in the case of using only the nearest neighbor nodes, alleviating the data sparsity problem and improving the knowledge representation performance.
[1]PHAN T, DO P. Building a Vietnamese question answering system based on knowledge graph and distributed CNN[J]. Neural Computing and Applications, 2021, 33(21): 14887-14907.
[2]MU S, LI Y, ZHAO W X, et al. Knowledge-guided disentangled representation learning for recommender systems[J]. ACM Transactions on Information Systems (TOIS), 2021, 40(1): 1-26.
[3]ZHAO X J, CHEN H, XING Z C, et al. Brain-inspired search engine assistant based on knowledge graph[J]. IEEE Transactions on Neural Networks and Learning Systems, 2021, 34(8):4386-4400.
[4]XIE Z, ZHU R, ZHAO K, et al. Dual gated graph attention networks with dynamic iterative training for cross-lingual entity alignment[J]. ACM Transactions on Information Systems (TOIS), 2021, 40(3): 1-30.
[5]BORDES A, USUNIER N, GARCIA-DURAN A, et al. Translating embeddings for modeling multi-relational data[J]. 2013, 2: 2787-2795.
[6]LIN H L, LIU Y, WANG W D, et al. Learning entity and relation embeddings for knowledge resolution[J]. Procedia Computer Science, 2017, 108: 345-354.
[7]WANG K, LIU Y, XU X, et al. Enhancing knowledge graph embedding by composite neighbors for link prediction[J]. Computing, 2020, 102(12): 2587-2606.
[8]NATHANI D, CHAUHAN J, SHARMA C, et al. Learning attention-based embeddings for relation prediction in knowledge graphs[C] //Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics. Stroudsburg, PA: Association for Computational Linguistics, 2020: 4710-4723.
[9]ZHU Q, ZHOU X, WU J, et al. Neighborhood-aware attentional representation for multilingual knowledge graphs [C]// Proceedings of the 28th International Joint Conference on Artificial Intelligence. China: IJCAI, 2019: 1943-1949.
[10] ZHANG Q J, WANG R G, YANG J, et al. Knowledge graph embedding by translating in time domain space for link prediction[J]. Knowledge-Based Systems, 2021, 212: 106564.
[11] DETTMERS T, MINERVINI P, STENETORPP, et al. Convolutional 2D knowledge graph embeddings [C]// Proceedings of the 32nd AAAI Conference on Artificial Intelligence. Menlo Park, CA: AAAI, 2018: 1811-1818.
[12] NGUYEN D Q, NGUYEN D Q, NGUYEN T D, et al. A convolutional neural network-based model for knowledge base completion and its application to search personalization[J]. Semantic Web, 2019, 10(5): 947-960.
[13] JI S, PAN S, CAMBRIA E, et al. A survey on knowledge graphs: Representation, acquisition, and applications[J]. IEEE Transactions on Neural Networks and Learning Systems, 2021, 33(2): 494-514.
[14] XIE R, LIU Z, JIA J, et al. Representation learning of knowledge graphs with entity descriptions [C]//Proceedings of the 30th AAAI Conference on Artificial Intelligence. Menlo Park, CA: AAAI, 2016: 2659-2665.
[15] ZHANG Q J, WANG R G, YANG J, et al. Structural context-based knowledge graph embedding for link prediction[J]. Neurocomputing, 2022, 470: 109-120.
[16] LI Z F, LIU H, ZHANG Z L, et al. Learning knowledge graph embedding with heterogeneous relation attention networks[J]. IEEE Transactions on Neural Networks and Learning Systems, 2021, 33(8): 3961-3973.
[17] PU F, ZHANG Z, FENG Y, et al. Learning context-based embeddings for knowledge graph completion[J]. Journal of Data and Information Science, 2022, 7(2): 84-106.
[18] BORREGO A, AYALA D, HERNÁNDEZ I, et al. CAFE: Knowledge graph completion using neighborhood-aware features[J]. Engineering Applications of Artificial Intelligence, 2021, 103: 104302.
[19] LI M D, SUN Z Y, ZHANG S H, et al. Enhancing knowledge graph embedding with relational constraints[J]. Neurocomputing, 2021, 429: 77-88.
[20] MAHESH B. Machine learning algorithms-a review[J]. International Journal of Science and Research, 2020, 9: 381-386.
[21] 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.
[22] 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: 1247-1249.
[23] SUN Z, DENG Z H, NIE J Y, et al.RotatE: knowledge graph embedding by relational rotation in complex space [DB/OL]//[2022-06-05].http://arxiv.org/pdf/1902.10197.
