Survey on Inductive Learning for Knowledge Graph Completion

doi:10.3778/j.issn.1673-9418.2303063

Abstract

Abstract: Knowledge graph completion can make knowledge graph more complete. However, traditional knowledge graph completion methods assume that all test entities and relations appear in the training process. Due to the evolving nature of real world KG, once unseen entities or relations appear, the knowledge graph needs to be retrained. Inductive learning for knowledge graph completion aims to complete triples containing unseen entities or unseen relations without training the knowledge graph from scratch, so it has received much attention in recent years. Firstly, starting from the basic concept of knowledge graph, this paper divides knowledge graph completion into two categories: transductive and inductive. Secondly, from the theoretical perspective of inductive knowledge graph completion, it is divided into two categories: semi-inductive and fully-inductive, and the models are summarized from this perspective. Then, from the technical perspective of inductive knowledge graph completion, it is divided into two categories: based on structural information and based on additional information. The methods based on structural information are subdivided into three categories: based on inductive embedding, based on logical rules and based on meta learning, and the methods based on additional information are subdivided into two categories: based on text information and other information. The current methods are further subdivided, analyzed and compared. Finally, it forecasts the main research directions in the future.

Key words: knowledge graph, knowledge graph completion, inductive learning

摘要： 知识图谱补全能够使知识图谱更加完整。然而，传统的知识图谱补全方法假定在测试时所有实体和关系都出现在训练过程，由于现实世界知识图谱的演变性质，一旦出现不可见实体或不可见关系，就需要重新训练知识图谱。面向知识图谱补全的归纳学习旨在补全包含不可见实体或不可见关系的三元组，而无需从头开始训练知识图谱，因此近年来受到广泛关注。首先从知识图谱的基本概念出发，将知识图谱补全分为两大类，直推式和归纳式；其次从归纳式的知识图谱补全的理论角度出发，分为半归纳和全归纳这两类，并从该角度对模型进行总结归纳；然后从归纳式的知识图谱补全的技术角度出发，分为基于结构信息和基于额外信息这两大类，将基于结构信息的方法细分为基于归纳嵌入、基于逻辑规则和基于元学习这三类，将基于额外信息的方法细分为基于文本信息和其他信息这两类，并对当下方法进一步深入细分、分析和对比；最后对未来的研究方向进行展望。

关键词: 知识图谱, 知识图谱补全, 归纳学习

LIANG Xinyu, SI Guannan, LI Jianxin, TIAN Pengxin, AN Zhaoliang, ZHOU Fengyu. Survey on Inductive Learning for Knowledge Graph Completion[J]. Journal of Frontiers of Computer Science and Technology, 2023, 17(11): 2580-2604.

梁新雨, 司冠南, 李建辛, 田鹏新, 安兆亮, 周风余. 面向知识图谱补全的归纳学习研究综述[J]. 计算机科学与探索, 2023, 17(11): 2580-2604.

References

[1] HUANG X, ZHANG J, LI D, et al. Knowledge graph embedding based question answering[C]//Proceedings of the 12th ACM International Conference on Web Search and Data Mining, Melbourne, Feb 2019. New York: ACM, 2019: 105-113.
[2] WANG X, WANG D, XU C, et al. Explainable reasoning over knowledge graphs for recommendation[C]//Proceedings of the 33rd AAAI Conference on Artificial Intelligence, the 31st Innovative Applications of Artificial Intelligence Con-ference, the 9th AAAI Symposium on Educational Advances in Artificial Intelligence, Hawaii, Jan 27-Feb 1, 2019. Menlo Park: AAAI, 2019: 5329-5336.
[3] JIA Y, QI Y, SHANG H, et al. A practical approach to constr-ucting a knowledge graph for cybersecurity[J]. Engineering, 2018, 4(1): 53-60.
[4] 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 Interna-tional Conference on Knowledge Discovery and Data Mining, New York, Aug 24-27, 2014. New York: ACM, 2014: 601-610.
[5] 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, Phoenix, Feb 12-17, 2016. Menlo Park: AAAI, 2016: 2659-2665.
[6] SHI B, WENINGER T. Open-world knowledge graph com-pletion[C]//Proceedings of the 32nd AAAI Conference on Artificial Intelligence, the 30th Innovative Applications of Artificial Intelligence, and the 8th AAAI Symposium on Educational Advances in Artificial Intelligence, New Orleans, Feb 2-7, 2018. Menlo Park: AAAI, 2018: 1957-1964.
[7] NIU L, FU C, YANG Q, et al. Open-world knowledge graph completion with multiple interaction attention[J]. World Wide Web, 2021, 24: 419-439.
[8] ZHANG C, YAO H, HUANG C, et al. Few-shot knowledge graph completion[C]//Proceedings of the 34th AAAI Conference on Artificial Intelligence, the 32nd Innovative Applications of Artificial Intelligence Conference, the 10th AAAI Symposium on Educational Advances in Artificial Intelligence, New York, Feb 7-12, 2020. Menlo Park: AAAI, 2020: 3041-3048.
[9] HENG J, GUO S, CHEN Z, et al. Adaptive attentional network for few-shot knowledge graph completion[J]. arXiv:2010.09638, 2020.
[10] WANG S, HUANG X, CHEN C, et al. Reform: error-aware few-shot knowledge graph completion[C]//Proceedings of the 30th ACM International Conference on Information & Knowledge Management, Queensland, Nov 1-5, 2021. New York: ACM, 2021: 1979-1988.
[11] HAMAGUCHI T, OIWA H, SHIMBO M, et al. Knowledge transfer for out-of-knowledge-base entities: a graph neural network approach[C]//Proceedings of the 26th International Joint Conference on Artificial Intelligence, Melbourne, Aug 19-25, 2017: 1802-1808.
[12] BI Z, ZHANG T, ZHOU P, et al. Knowledge transfer for out-of-knowledge-base entities: improving graph-neural-network-based embedding using convolutional layers[J]. IEEE Access, 2020, 8: 159039-159049.
[13] ZHAO M, JIA W, HUANG Y. Attention-based aggregation graph networks for knowledge graph information transfer[C]//LNCS 12085: Proceedings of the 24th Pacific-Asia Conference of Advances in Knowledge Discovery and Data Mining, Singapore, May 11-14, 2020. Cham: Springer, 2020: 542-554.
[14] WANG C, ZHOU X, PAN S, et al. Exploring relational semantics for inductive knowledge graph completion[C]//Proceedings of the 36th AAAI Conference on Artificial Intelligence, the 34th Conference on Innovative Applications of Artificial Intelligence, the 12th Symposium on Educational Advances in Artificial Intelligence, Feb 22-Mar 1, 2022. Menlo Park: AAAI, 2022: 4184-4192.
[15] ALI M, BERRENDORF M, GALKIN M, et al. Improving inductive link prediction using hyper-relational facts[C]//LNCS 12922: Proceedings of the 20th International Semantic Web Conference, Albany, Oct 24-28, 2021. Cham: Springer: 2021: 74-92.
[16] GESESE G A, SACK H, ALAM M. RAILD: towards leveraging relation features for inductive link prediction in knowledge graphs[J]. arXiv:2211.11407, 2022.
[17] WANG P, HAN J, LI C, et al. Logic attention based neighborhood aggregation for inductive knowledge graph embedding[C]//Proceedings of the 33rd AAAI Conference on Artificial Intelligence, the 31st Innovative Applications of Artificial Intelligence Conference, the 9th AAAI Symposium on Educational Advances in Artificial Intelligence, Hawaii, Jan 27-Feb 1, 2019. Menlo Park: AAAI, 2019: 7152-7159.
[18] LI M, SUN Z, ZHANG W. SLAN: similarity-aware agg-regation network for embedding out-of-knowledge-graph entities[J]. Neurocomputing, 2022, 491: 186-196.
[19] REN C, ZHANG L, FANG L, et al. Ontological concept structure aware knowledge transfer for inductive knowledge graph embedding[C]//Proceedings of the 2021 International Joint Conference on Neural Networks, Shenzhen, Jul 18-22, 2021. Piscataway: IEEE, 2021: 1-8.
[20] ZHONG S, YUE K, DUAN L. Attention-based relation prediction of knowledge graph by incorporating graph and context features[C]//LNCS 13724: Proceedings of the 23rd International Conference on Web Information Systems Engineering, Biarritz, Nov 1-3, 2022. Cham: Springer, 2022: 259-273.
[21] 杜治娟, 杜治蓉, 王璐. 基于相邻和语义亲和力的开放知识图谱表示学习[J]. 计算机研究与发展, 2019, 56(12): 2549- 2561.
DU Z J, DU Z R, WANG L. Open knowledge graph represen-tation learning based on neighbors and semantic affinity[J]. Journal of Computer Research and Development, 2019, 56(12): 2549-2561.
[22] ALBOOYEH M, GOEL R, KAZEMI S M. Out-of-sample representation learning for knowledge graphs[C]//Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing, Punta Cana, Nov 16-20, 2020. Stroud-sburg: ACL, 2020: 2657-2666.
[23] DAI D, ZHENG H, LUO F, et al. Inductively representing out-of-knowledge-graph entities by optimal estimation under translational assumptions[C]//Proceedings of the 6th Workshop on Representation Learning for NLP, Bangkok, Aug 6, 2021. Stroudsburg: ACL, 2021: 83-89.
[24] BHOWMIK R, DE MELO G. Explainable link prediction for emerging entities in knowledge graphs[C]//Proceedings of the 19th International Semantic Web Conference, Athens, Nov 2-6, 2020. Cham: Springer, 2020: 39-55.
[25] HE Y, WANG Z, ZHANG P, et al. VN network: embedding newly emerging entities with virtual neighbors[C]//Proceedings of the 29th ACM International Conference on Information & Knowledge Management, Ireland, Oct 19-23, 2020. New York: ACM, 2020: 505-514.
[26] CUI Y, WANG Y, SUN Z, et al. Inductive knowledge graph reasoning for multi-batch emerging entities[C]//Proceedings of the 31st ACM International Conference on Information & Knowledge Management, Atlanta, Oct 17-22, 2022. New York: ACM, 2022: 335-344.
[27] BAEK J, LEE D B, HWANG S J. Learning to extrapolate knowledge: transductive few-shot out-of-graph link prediction[C]//Advances in Neural Information Processing Systems 33, Dec 6-12, 2020: 546-560.
[28] ZHANG Y, WANG W, CHEN W, et al. Meta-learning based hyper-relation feature modeling for out-of-knowledge-base embedding[C]//Proceedings of the 30th ACM International Conference on Information & Knowledge Management, Queensland, Nov 1-5, 2021. New York: ACM, 2021: 2637-2646.
[29] XIE R, LIU Z, LUAN H, et al. Image-embodied knowledge representation learning[C]//Proceedings of the 26th Inter-national Joint Conference on Artificial Intelligence, Melbourne, Aug 19-25, 2017. Menlo Park: AAAI, 2017: 3140-3146.
[30] PEZESHKPOUR P, CHEN L, SINGH S. Embedding multi-modal relational data for knowledge base completion[C]//Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, Brussels, Oct 31-Nov 4, 2018. Stroudsburg: ACL, 2018: 3208-3218.
[31] WANG Z, LI L, LI Q, et al. Multimodal data enhanced representation learning for knowledge graphs[C]//Proceedings of the 2019 International Joint Conference on Neural Networks, Budapest, Jul 14-19, 2019. Piscataway: IEEE, 2019: 1-8.
[32] LIANG S, ZHU A, ZHANG J, et al. Hyper-node relational graph attention network for multi-modal knowledge graph completion[J]. ACM Transactions on Multimedia Computing, Communications and Applications, 2023, 19(2): 1-21.
[33] ZHENG S, WANG W, QU J, et al. MMKGR: multi-hop multi-modal knowledge graph reasoning[J]. arXiv:2209.01416, 2022.
[34] HAO Y, CAO X, FANG Y, et al. Inductive link prediction for nodes having only attribute information[C]//Proceedings of the 29th International Conference on International Joint Conferences on Artificial Intelligence, Yokohama, Jan 7-15, 2021. New York: ACM, 2021: 1209-1215.
[35] LI Y, HE D, BAN Z. Learning node embedding for inductive link prediction in sparse observation network[C]//Proceedings of the 2022 International Joint Conference on Neural Net-works, Padua, Jul 18-23, 2022. Piscataway: IEEE, 2022: 1-7.
[36] ZHANG D, YIN J, PHILIP S Y. Link prediction with contextualized self-supervision[J]. IEEE Transactions on Knowledge and Data Engineering, 2022: 1-14.
[37] DING Z, WU J, HE B, et al. Few-shot inductive learning on temporal knowledge graphs using concept-aware information[J]. arXiv:2211.08169, 2022.
[38] WANG R, LI Z, SUN D, et al. Learning to sample and aggregate: few-shot reasoning over temporal knowledge graphs[J]. arXiv:2210.08654, 2022.
[39] GENG Y, CHEN J, ZHANG W, et al. Disentangled ontology embedding for zero-shot learning[C]//Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, Washington, Aug 14-18, 2022. New York: ACM, 2022: 443-453.
[40] XIONG W, YU M, CHANG S, et al. One-shot relational learning for knowledge graphs[C]//Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, Brussels, Oct 31-Nov 4, 2018. Stroudsburg: ACL, 2018: 1980-1990.
[41] JIANG Z, GAO J, LV X. MetaP: meta pattern learning for one-shot knowledge graph completion[C]//Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval, Canada, Jul 11-15, 2021. New York: ACM, 2021: 2232-2236.
[42] XU J, ZHANG J, KE X, et al. P-INT: a path-based inter-action model for few-shot knowledge graph completion[C]//Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, Punta Cana, Nov 7-11, 2021. Stroudsburg: ACL, 2021: 385-394.
[43] WU Y, TIAN L, HUI B, et al. Learning discriminative representation for few-shot knowledge graph completion[C]//Proceedings of the 7th International Conference on Intelligent Information Processing, Bucharest, Sep 29-30, 2022. New York: ACM, 2022: 1-5.
[44] CHEN M, ZHANG W, ZHANG W, et al. Meta relational learning for few-shot link prediction in knowledge graphs[C]//Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th Inter-national Joint Conference on Natural Language Processing, Hong Kong, China, Nov 3-7, 2019. Stroudsburg: ACL, 2019: 4217-4226.
[45] NIU G, LI Y, TANG C, et al. Relational learning with gated and attentive neighbor aggregator for few-shot knowledge graph completion[C]//Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval, Canada, Jul 11-15, 2021. New York: ACM, 2021: 213-222.
[46] WU H, YIN J, RAJARATNAM B, et al. Hierarchical rela-tional learning for few-shot knowledge graph completion[J]. arXiv:2209.01205, 2022.
[47] LV X, GU Y, HAN X, et al. Adapting meta knowledge graph information for multi-hop reasoning over few-shot relations[C]//Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th Inter-national Joint Conference on Natural Language Processing, Hong Kong, China, Nov 3-7, 2019. Stroudsburg: ACL, 2019: 3376-3381.
[48] ZHANG C, YU L, SAEBI M, et al. Few-shot multi-hop relation reasoning over knowledge bases[C]//Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing, Punta Cana, Nov 16-20, 2020. Strou-dsburg: ACL, 2020: 580-585.
[49] QIN P, WANG X, CHEN W, et al. Generative adversarial zero-shot relational learning for knowledge graphs[C]//Proceedings of the 34th AAAI Conference on Artificial Intelligence, the 32nd Innovative Applications of Artificial Intelligence Conference, the 10th AAAI Symposium on Educational Advances in Artificial Intelligence, New York, Feb 7-12, 2020. Menlo Park: AAAI, 2020: 8673-8680.
[50] GENG Y, CHEN J, CHEN Z, et al. OntoZSL: ontology-enhanced zero-shot learning[C]//Proceedings of the 30th World Wide Web Conference, Ljubljana, Apr 19-23, 2021. New York: ACM, 2021: 3325-3336.
[51] LIU X, GUO Y, HUANG M, et al. Stochastic and dual adversarial GAN-boosted zero-shot knowledge graph[C]//LNCS 13606: Proceedings of the 2nd CAAI International Conference on Artificial Intelligence, Beijing, Aug 27-28, 2022. Cham: Springer, 2022: 55-67.
[52] LI X, MA J, YU J, et al. A structure-enhanced generative adversarial network for knowledge graph zero-shot relational learning[J]. Information Sciences, 2023, 629: 169-183.
[53] LI X, MA J, YU J, et al. HAPZSL: a hybrid attention prototype network for knowledge graph zero-shot relational learning[J]. Neurocomputing, 2022, 508: 324-336.
[54] SONG R, HE S, ZHENG S, et al. Ontology-guided and text-enhanced representation for knowledge graph zero-shot relational learning[C]//Proceedings of the 10th International Conference on Learning Representations on Deep Learning on Graphs for Natural Language Processing, Apr 25-29, 2022.
[55] HE S, ZHENG S, et al. Decoupling mixture-of-graphs: unseen relational learning for knowledge graph completion by fusing ontology and textual experts[C]//Proceedings of the 29th International Conference on Computational Linguistics, Gyeongju, Oct 12-17, 2022. Stroudsburg: ACL, 2022: 2237-2246.
[56] WANG J, WANG X, LUO X, et al. Open-world relationship prediction[C]//Proceedings of the 32nd International Con-ference on Tools with Artificial Intelligence, Baltimore, Nov 9-11, 2020. Piscataway: IEEE, 2020: 323-330.
[57] CUI Y, WANG Y, SUN Z, et al. Lifelong embedding learning and transfer for growing knowledge graphs[J]. arXiv:2211.15845, 2022.
[58] GALáRRAGA L A, TEFLIOUDI C, HOSE K, et al. AMIE: association rule mining under incomplete evidence in ontological knowledge bases[C]//Proceedings of the 22nd International Conference on World Wide Web, Rio de Janeiro, May 13-17, 2013. New York: ACM, 2013: 413-422.
[59] GALáRRAGA L, TEFLIOUDI C, HOSE K, et al. Fast rule mining in ontological knowledge bases with AMIE+[J]. The VLDB Journal, 2015, 24(6): 707-730.
[60] MEILICKE C, FINK M, WANG Y, et al. Fine-grained evalua-tion of rule-and embedding-based systems for knowledge graph completion[C]//LNCS 11136: Proceedings of the 17th International Semantic Web Conference, Monterey, Oct 8-12, 2018. Cham: Springer, 2018: 3-20.
[61] MEILICKE C, CHEKOL M W, RUFFINELLI D, et al. Anytime bottom-up rule learning for knowledge graph completion[C]//Proceedings of the 28th International Joint Conference on Artificial Intelligence, Macao, Aug 10-16, 2019. Menlo Park: AAAI, 2019: 3137-3143.
[62] YANG F, YANG Z, COHEN W W. Differentiable learning of logical rules for knowledge base reasoning[C]//Proceedings of the 31st International Conference on Neural Information Processing Systems, Long Beach, Dec 4-9, 2017. New York: Curran Associates Inc, 2017: 2316-2325.
[63] SADEGHIAN A, ARMANDPOUR M, DING P, et al. Drum: end-to-end differentiable rule mining on knowledge graphs[J]. arXiv:1911.00055, 2019.
[64] QU M, CHEN J, XHONNEUX L P, et al. RNNLogic: learning logic rules for reasoning on knowledge graphs[J]. arXiv:2010.04029, 2020.
[65] ZHANG Y, LI Y, ZHANG Y, et al. Missing-edge aware knowledge graph inductive inference through dual graph learning and traversing[J]. Expert Systems with Applications, 2023, 213: 118969.
[66] ZHU Z, ZHANG Z, XHONNEUX L P, et al. Neural bellman-ford networks: a general graph neural network framework for link prediction[C]//Advances in Neural Information Processing Systems 34, Dec 6-14, 2021: 29476-29490.
[67] LIU S, GRAU B, HORROCKS I, et al. INDIGO: GNN-based inductive knowledge graph completion using pair-wise encoding[C]//Advances in Neural Information Processing Systems 34, Dec 6-14, 2021: 2034-2045.
[68] YAN Z, MA T, GAO L, et al. Cycle representation learning for inductive relation prediction[C]//Proceedings of the 2022 International Conference on Machine Learning, Baltimore, Jul 17-23, 2022: 24895-24910.
[69] ZHANG Y, YAO Q. Knowledge graph reasoning with relational digraph[C]//Proceedings of the ACM Web Con-ference 2022, Lyon, Apr 25-29, 2022. New York: ACM, 2022: 912-924.
[70] TERU K K, DENIS E G, HAMILTON W L. Inductive relation prediction by subgraph reasoning[C]//Proceedings of the 37th International Conference on Machine Learning, Jul 13-18, 2020: 9448-9457.
[71] CHEN J, HE H, WU F, et al. Topology-aware correlations between relations for inductive link prediction in knowledge graphs[C]//Proceedings of the 35th AAAI Conference on Artificial Intelligence, the 33rd Innovative Applications of Artificial Intelligence Conference, the 11th AAAI Symposium on Educational Advances in Artificial Intelligence, New York, Feb 2-9, 2021. Menlo Park: AAAI, 2021: 6271-6278.
[72] MAI S, ZHENG S, YANG Y, et al. Communicative message passing for inductive relation reasoning[C]//Proceedings of the 35th AAAI Conference on Artificial Intelligence, the 33rd Innovative Applications of Artificial Intelligence Conference, the 11th AAAI Symposium on Educational Advances in Artificial Intelligence, New York, Feb 2-9, 2021. Menlo Park: AAAI, 2021: 4294-4302.
[73] PAN Y, LIU J, ZHANG L, et al. Learning first-order rules with relational path contrast for inductive relation reasoning[J]. arXiv:2110.08810, 2021.
[74] MAI S, ZHENG S, SUN Y, et al. Dynamic graph dropout for subgraph-based relation prediction[J]. Knowledge-Based Systems, 2022, 250: 109172.
[75] KWAK H, JUNG H B K. Subgraph representation learning with hard negative samples for inductive link prediction[C]//Proceedings of the 2022 IEEE International Conference on Acoustics, Speech and Signal Processing, Singapore, May 22-27, 2022. Piscataway: IEEE, 2022: 4768-4772.
[76] ZHENG S, MAI S, SUN Y, et al. Subgraph-aware few-shot inductive link prediction via meta-learning[J]. IEEE Tran-sactions on Knowledge and Data Engineering, 2023, 35(6): 6512-6517.
[77] WANG H, REN H, LESKOVEC J. Relational message passing for knowledge graph completion[C]//Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, Singapore, Aug 14-18, 2021. New York: ACM, 2021: 1697-1707.
[78] XU X, ZHANG P, HE Y, et al. Subgraph neighboring relations infomax for inductive link prediction on knowledge graphs[J]. arXiv:2208.00850, 2022.
[79] CHEN Z, YU H, LI J, et al. Entity representation by neigh-boring relations topology for inductive relation prediction[C]//LNCS 13630: Proceedings of the 19th Pacific Rim International Conference on Artificial Intelligence, Shanghai, Nov 10-13, 2022. Cham: Springer, 2022: 59-72.
[80] LIN Q, LIU J, XU F, et al. Incorporating context graph with logical reasoning for inductive relation prediction[C]//Proceedings of the 45th International ACM SIGIR Con-ference on Research and Development in Information Retrieval, Madrid, Jul 11-15, 2022. New York: ACM, 2022: 893-903.
[81] CHEN M, ZHANG W, ZHU Y, et al. Meta-knowledge transfer for inductive knowledge graph embedding[C]//Proceedings of the 45th International ACM SIGIR Con-ference on Research and Development in Information Retrieval, Madrid, Jul 11-15, 2022. New York: ACM, 2022: 927-937.
[82] XIE W, WANG S, WEI Y, et al. Dynamic knowledge graph completion with jointly structural and textual dependency[C]//LNCS 12453: Proceedings of the 20th International Conference on Algorithms and Architectures for Parallel Processing, New York, Oct 2-4, 2020. Cham: Springer, 2020: 432-448.
[83] CHEN X, JIA S, DING L, et al. SDT: an integrated model for open-world knowledge graph reasoning[J]. Expert Systems with Applications, 2020, 162: 113889.
[84] SHAH H, VILLMOW J, ULGES A, et al. An open-world extension to knowledge graph completion models[C]//Proceedings of the 33rd AAAI Conference on Artificial Intelligence, the 31st Innovative Applications of Artificial Intelligence Conference, the 9th AAAI Symposium on Educational Advances in Artificial Intelligence, Hawaii, Jan 27-Feb 1, 2019. Menlo Park: AAAI, 2019: 3044-3051.
[85] ZHOU Y, SHI S, HUANG H. Weighted aggregator for the open-world knowledge graph completion[C]//Proceedings of the 6th International Conference of Pioneering Computer Scientists, Engineers and Educators, Taiyuan, Sep 18-21, 2020. Singapore: Springer, 2020: 283-291.
[86] SHAH H, VILLMOW J, ULGES A. Relation specific trans-formations for open world knowledge graph completion[C]//Proceedings of the Graph-Based Methods for Natural Language Processing, Barcelona, Oct 12-17, 2020. Stroudsburg: ACL, 2020: 79-84.
[87] ZHU W, ZHI X, TONG W. Extracting short entity descriptions for open-world extension to knowledge graph completion models[C]//LNCS 12274: Proceedings of the 13th Interna-tional Conference on Knowledge Science, Engineering and Management, Hangzhou, Aug 28-30, 2020. Cham: Springer, 2020: 16-27.
[88] WANG Y, XIAO W, TAN Z, et al. CAPS-OWKG: a capsule network model for open-world knowledge graph[J]. Inter-national Journal of Machine Learning and Cybernetics, 2021, 12(6): 1627-1637.
[89] WANG J, LEI J, SUN S, et al. Embeddings based on relation-specific constraints for open world knowledge graph completion[J]. Applied Intelligence, 2023, 53(12): 16192-16204.
[90] CLOUATRE L, TREMPE P, ZOUAQ A, et al. MLMLM: link prediction with mean likelihood masked language model[C]//Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics, the 11th Inter-national Joint Conference on Natural Language Processing, Aug 1-6, 2021. Stroudsburg: ACL, 2021: 4321-4331.
[91] WANG X, GAO T, ZHU Z, et al. Kepler: a unified model for knowledge embedding and pre-trained language repre-sentation[J]. Transactions of the Association for Compu-tational Linguistics, 2021, 9: 176-194.
[92] DAZA D, COCHEZ M, GROTH P. Inductive entity repres-entations from text via link prediction[C]//Proceedings of the 30th World Wide Web Conference, Ljubljana, Apr 19-23, 2021. New York: ACM, 2021: 798-808.
[93] MARKOWITZ E, BALASUBRAMANIAN K, MIRTAHERI M, et al. Statik: structure and text for inductivive know-ledge graph completion[C]//Proceedings of the 2022 Con-ference of the North American Chapter of the Association for Computational Linguistics, Seattle, Jul 10-15, 2022. Stroudsburg: ACL, 2022: 604-615.
[94] ZHANG N, XIE X, CHEN X, et al. Reasoning through memorization: nearest neighbor knowledge graph embeddings[J]. arXiv:2201.05575, 2022.
[95] WANG L, ZHAO W, WEI Z, et al. SimKGC: simple contrastive knowledge graph completion with pre-trained language models[C]//Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics, Dublin, May 22-27, 2022. Stroudsburg: ACL, 2022: 4281-4294.
[96] LV X, LIN Y, CAO Y, et al. Do pre-trained models benefit knowledge graph completion? A reliable evaluation and a reasonable approach[C]//Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics, Dublin, May 22-27, 2022. Stroudsburg: ACL, 2022: 3570-3581.
[97] PENG B, LIANG S, ISLAM M. Bi-link: bridging inductive link predictions from text via contrastive learning of transformers and prompts[J]. arXiv:2210.14463, 2022.
[98] LI D, YANG S, XU K, et al. Multi-task pre-training language model for semantic network completion[J]. arXiv:2201. 04843, 2022.
[99] NADKARNI R, WADDEN D, BELTAGY I, et al. Scientific language models for biomedical knowledge base completion: an empirical study[J]. arXiv:2106.09700, 2021.
[100] WU J, MAI S, HU H. Contextual relation embedding and interpretable triplet capsule for inductive relation prediction[J]. Neurocomputing, 2022, 505: 80-91.
[101] LIN Q, MAO R, LIU J, et al. Fusing topology contexts and logical rules in language models for knowledge graph completion[J]. Information Fusion, 2023, 90: 253-264.
[102] KARTHIK V, TRIPATHI B, KHAPRA M M, et al. A joint training framework for open-world knowledge graph embeddings[C]//Proceedings of the 3rd Conference on Automated Knowledge Base Construction, Oct 4-8, 2021.
[103] WANG B, WANG G, HUANG J, et al. Inductive learning on commonsense knowledge graph completion[C]//Procee- dings of the 2021 Conference of the International Joint Conference on Neural Networks， Shenzhen, Jul 18-22, 2021: 1-8.
[104] SUN H, ZHONG J, MA Y, et al. Timetraveler: reinfor-cement learning for temporal knowledge graph forecasting[C]//Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, Punta Cana, Nov 7-11, 2021. Stroudsburg: ACL, 2021: 8306-8319.
[105] DING Z, WU J, HE B, et al. Few-shot inductive learning on temporal knowledge graphs using concept-aware infor-mation[J]. arXiv:2211.08169, 2022.
[106] MEI X, YANG L, CAI X, et al. An adaptive logical rule embedding model for inductive reasoning over temporal knowledge graphs[C]//Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, Abu Dhabi, Dec 7-11, 2022. Stroudsburg: ACL, 2022: 7304- 7316.
[107] DING Z, WU J, LI Z, et al. Improving few-shot inductive learning on temporal knowledge graphs using confidence-augmented reinforcement learning[J]. arXiv:2304.00613, 2023.
[108] HAN Z, CHEN P, MA Y, et al. xERTE: explainable reasoning on temporal knowledge graphs for forecasting future links[J]. arXiv:2012.15537, 2020.
[109] GENG Y, CHEN J, ZHANG W, et al. Relational message passing for fully inductive knowledge graph completion[J]. arXiv:2210.03994, 2022.
[110] WU J, MAI S, HU H. Relation-dependent contrastive learning with cluster sampling for inductive relation prediction[J]. arXiv:2211.12266, 2022.
[111] HUANG Q, REN H, LESKOVEC J. Few-shot relational reasoning via connection subgraph pretraining[J]. arXiv:2210.06722, 2022.
[112] CHEN M, ZHANG W, YAO Z, et al. Meta-learning based knowledge extrapolation for knowledge graphs in the federated setting[C]//Proceedings of the 31st International Joint Conference on Artificial Intelligence, Vienna, Jul 23-29, 2022.
[113] WANG Z, LAI K P, LI P, et al. Tackling long-tailed relations and uncommon entities in knowledge graph completion[C]//Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing, the 9th International Joint Conference on Natural Language Processing, Hong Kong, China, Nov 3-7, 2019. Stroudsburg: ACL, 2019: 250-260.
[114] OH B, SEO S, HWANG J, et al. Open-world knowledge graph completion for unseen entities and relations via attentive feature aggregation[J]. Information Sciences, 2022, 586: 468-484.
[115] YAO L, MAO C, LUO Y. KG-BERT: BERT for knowledge graph completion[J]. arXiv:1909.03193, 2019.
[116] KIM B, HONG T, KO Y, et al. Multi-task learning for knowledge graph completion with pre-trained language models[C]//Proceedings of the 28th International Confer-ence on Computational Linguistics, Barcelona, Dec 8-13, 2020. Stroudsburg: ACL, 2020: 1737-1743.
[117] WANG B, SHEN T, LONG G, et al. Structure-augmented text representation learning for efficient knowledge graph completion[C]//Proceedings of the 30th World Wide Web Conference, Ljubljana, Apr 19-23, 2021. New York: ACM, 2021: 1737-1748.
[118] ZHA H, CHEN Z, YAN X. Inductive relation prediction by BERT[C]//Proceedings of the 36th AAAI Conference on Artificial Intelligence, the 34th Conference on Innovative Applications of Artificial Intelligence, the 12th Symposium on Educational Advances in Artificial Intelligence, Feb 22-Mar 1, 2022. Menlo Park: AAAI, 2022: 5923-5931.
[119] CHEN Z, XU C, SU F, et al. Meta-learning based knowledge extrapolation for temporal knowledge graph[J]. arXiv:2302.05640, 2023.
[120] HU Z, GUTIéRREZ-BASULTO V, XIANG Z, et al. Type-aware embeddings for multi-hop reasoning over knowledge graphs[J]. arXiv:2205.00782, 2022.
[121] HAMILTON W L, YING R, LESKOVEC J. Inductive representation learning on large graphs[J]. arXiv:1706. 02216, 2017.
[122] ZENG H, ZHOU H, SRIVASTAVA A, et al. Graphsaint: graph sampling based inductive learning method[J]. arXiv:1907.04931, 2019.
[123] MIKOLOV T, CHEN K, CORRADO G, et al. Efficient estimation of word representations in vector space[J]. arXiv:1301.3781, 2013.
[124] PENNINGTON J, SOCHER R, MANNING C D. Glove: global vectors for word representation[C]//Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing, Doha, Oct 25-29, 2014. Stroudsburg: ACL, 2014: 1532-1543.
[125] DEVLIN J, CHANG M W, LEE K, et al. BERT: pre-training of deep bidirectional transformers for language understanding[J]. arXiv:1810.04805, 2018.
[126] LIU Y, OTT M, GOYAL N, et al. Roberta: a robustly optimized BERT pretraining approach[J]. arXiv:1907.11692, 2019.
[127] AUER S, BIZER C, KOBILAROV G, et al. Dbpedia: a nucleus for a web of open data[C]//LNCS 4825: Proceedings of the 6th International Semantic Web Conference, the 2nd Asian Semantic Web Conference, Busan, Nov 11-15, 2007. Berlin, Heidelberg: Springer, 2007: 722-735.
[128] 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, Vancouver, Jun 10-12, 2008. New York: ACM, 2008: 1247-1250.