基于图神经网络与元学习的小样本关系推理模型

doi:10.19678/j.issn.1000-3428.0069130

摘要/Abstract

摘要： 知识图谱关系推理旨在推理实体间缺失的链接,当前知识图谱关系推理模型在小样本关系推理上表现不佳,且难以对训练集中未出现的实体进行关系推理。针对以上问题,提出一种基于图神经网络(GNN)与损失权重元学习的知识图谱小样本关系归纳推理模型。模型利用图神经网络学习目标实体间的子图模式,从而泛化到新实体的关系推理。通过路径掩码策略降低模型对特定子图模式的依赖,捕捉数据中的关键特征和模式,从而提高模型归纳推理泛化能力。基于元学习方法引入分布均衡的元数据集来学习一个自适应损失函数,调整不同样本的损失权重,使模型更关注难以预测的小样本关系,从而提高模型对小样本关系预测的准确度。最后,在归纳链接预测基准数据集FB15k-237和NELL-995中过滤掉没有子图的三元组,并进行链接预测和三元组分类任务,同时对测试集中属于小样本关系的三元组进行评价。实验结果表明,所提模型在归纳推理基准数据集上具有较好的表现,并且在7个小样本数据集上的性能比目前最优的模型平均提升1%左右。

关键词: 知识图谱, 图神经网络, 小样本关系预测, 路径掩码, 损失权重元学习

Abstract: Knowledge graph relation reasoning aims to infer missing links between entities. Current knowledge graph relation reasoning models perform poorly when reasoning with few-shot relations and struggle to reason for entities that are not seen during training. To address these issues, this study proposes a knowledge graph few-shot relation inductive reasoning model based on Graph Neural Network (GNN) and loss-weight meta-learning. The model utilizes GNN to learn the subgraph patterns between target entities, thereby generalizing to relation reasoning for new entities. The path-wise masking strategy reduces the reliance of the model on specific subgraph patterns and captures the key features and patterns in the data, thereby enhancing the inductive reasoning and generalization capabilities of the model. A distribution-balanced meta-dataset based on meta-learning is introduced to learn the adaptive loss function. The loss weights of different samples are adjusted, enabling the model to focus more on challenging few-shot relations, thereby improving the accuracy of the few-shot relation prediction. Finally, triplets without subgraphs in inductive link prediction benchmark datasets FB15k-237 and NELL-995 are filtered out, and link prediction and triplet classification tasks are performed. Simultaneously, triplets belonging to few-shot relations in the test set are evaluated. Experimental results show that the proposed model exhibits the best performance on the inductive reasoning benchmark datasets and achieves an average improvement of approximately 1% over current state-of-the-art models on seven few-shot datasets.

Key words: knowledge graph, Graph Neural Network (GNN), few-shot relation prediction, path-wise masking, loss-weight meta-learning

中图分类号:

TP18

刘文杰, 陈亮, 任智杰. 基于图神经网络与元学习的小样本关系推理模型[J]. 计算机工程, 2025, 51(5): 124-132.

LIU Wenjie, CHEN Liang, REN Zhijie. Few-shot Relation Reasoning Model Based on Graph Neural Network and Meta-Learning[J]. Computer Engineering, 2025, 51(5): 124-132.

https://www.ecice06.com/CN/Y2025/V51/I5/124

参考文献

[1] 许鑫冉,王腾宇,鲁才.图神经网络在知识图谱构建与应用中的研究进展[J].计算机科学与探索, 2023, 17(10):2278-2299. XU X R, WANG T Y, LU C. Research progress of graph neural network in knowledge graph construction and application[J]. Journal of Frontiers of Computer Science and Technology, 2023, 17(10):2278-2299.(in Chinese)
[2] 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, 2022, 33(2):494-514.
[3] CAO Y X, WANG X, HE X N, et al. Unifying knowledge graph learning and recommendation:towards a better understanding of user preferences[C]//Proceedings of the World Wide Web Conference. New York, USA:ACM Press, 2019:151-161.
[4] ZENG X X, TU X Q, LIU Y S, et al. Toward better drug discovery with knowledge graph[J]. Current Opinion in Structural Biology, 2022, 72:114-126.
[5] BORDES A, USUNIER N, GARCIA-DURÁN A, et al. Translating embeddings for modeling multi-relational data[C]//Proceedings of the 27th International Conference on Neural Information Processing Systems. New York, USA:ACM Press, 2013:2787-2795.
[6] LIN Y K, LIU Z Y, SUN M S, et al. Learning entity and relation embeddings for knowledge graph completion[C]//Proceedings of the 29th AAAI Conference on Artificial Intelligence. New York, USA:ACM Press, 2015:2181-2187.
[7] DETTMERS T, MINERVINI P, STENETORP P, et al. Convolutional 2D knowledge graph embeddings[C]//Proceedings of the 32nd AAAI Conference on Artificial Intelligence and 30th Innovative Applications of Artificial Intelligence Conference and 8th AAAI Symposium on Educational Advances in Artificial Intelligence. New York, USA:ACM Press, 2018:1811-1818.
[8] SUN Z, DENG Z, NIE J, et al. RotatE:knowledge graph embedding by relational rotation in complex space[C]//Proceedings of the 7th International Conference on Learning Representations. New York, USA:ACM Press, 2019:1-18.
[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.(in Chinese)
[10] TERU K K, DENIS E G, HAMILTON W L, et al. Inductive relation prediction by subgraph reasoning[C]//Proceedings of the 37th International Conference on Machine Learning. New York, USA:ACM Press, 2020:9448-9457.
[11] MEILICKE C, FINK M, WANG Y J, et al. Fine-grained evaluation of rule-and embedding-based systems for knowledge graph completion[C]//Proceedings of the 17th International Semantic Web Conference. Berlin, Germany:Springer, 2018:3-20.
[12] LI Y L, YU K, ZHANG Y H, et al. Learning relation-specific representations for few-shot knowledge graph completion[EB/OL].[2023-10-08] . https://arxiv.org/abs/2203.11639v2.
[13] ZHENG S J, MAI S J, SUN Y, et al. Subgraph-aware few-shot inductive link prediction via meta-learning[J]. IEEE Transactions on Knowledge and Data Engineering, 2022, 35(6):6512-6517.
[14] SCHLICHTKRULL M, KIPF T N, BLOEM P, et al. Modeling relational data with graph convolutional networks[C]//Proceedings of the 17th International Semantic Web Conference. Berlin, Germany:Springer, 2018:593-607.
[15] YE R, LI X, FANG Y J, et al. A vectorized relational graph convolutional network for multi-relational network alignment[C]//Proceedings of the 28th International Joint Conference on Artificial Intelligence. New York, USA:ACM Press, 2019:4135-4141.
[16] HAMILTON W L, YING R, LESKOVEC J, et al. Inductive representation learning on large graphs[C]//Proceedings of the 31st International Conference on Neural Information Processing Systems. New York, USA:ACM Press, 2017:1025-1035.
[17] 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, USA:ACL, 2019:4710-4723.
[18] 官赛萍,靳小龙,贾岩涛,等.面向知识图谱的知识推理研究进展[J].软件学报, 2018, 29(10):2966-2994. GUAN S P, JIN X L, JIA Y T, et al. Knowledge reasoning over knowledge graph:a survey[J]. Journal of Software, 2018, 29(10):2966-2994.(in Chinese)
[19] LI S, XU H R, LU Z D. Generalize symbolic knowledge with neural rule engine[EB/OL].[2023-10-08] . https://arxiv.org/abs/1808.10326v3.
[20] SADEGHIAN A, ARMANDPOUR M, DING P, et al. DRUM:end-to-end differentiable rule mining on knowledge graphs[EB/OL].[2023-10-08] . https://arxiv.org/abs/1911.00055?context=cs.LO.
[21] MAI S J, ZHENG S J, YANG Y D, et al. Communicative message passing for inductive relation reasoning[J]. Proceedings of the AAAI Conference on Artificial Intelligence, 2021, 35(5):4294-4302.
[22] ZHANG Y Q, YAO Q M, ZHANG Y Q, et al. Knowledge graph reasoning with relational digraph[C]//Proceedings of the 2022 ACM Web Conference. New York, USA:ACM Press, 2022:912-924.
[23] XIONG W H, YU M, CHANG S Y, et al. One-shot relational learning for knowledge graphs[C]//Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing. Stroudsburg, USA:ACL, 2018:1980-1990.
[24] ZHANG C X, YAO H X, HUANG C, et al. Few-shot knowledge graph completion[J]. Proceedings of the AAAI Conference on Artificial Intelligence, 2020, 34(3):3041-3048.
[25] SHENG J W, GUO S, CHEN Z Y, et al. Adaptive attentional network for few-shot knowledge graph completion[C]//Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP). Stroudsburg, USA:ACL, 2020:1681-1691.
[26] YANG R T, WEI Z C, FAN Y J, et al. A few-shot inductive link prediction model in knowledge graphs[J]. IEEE Access, 2022, 10:97370-97380.
[27] LI J T, WU R F, SUN W B, et al. What's behind the mask:understanding masked graph modeling for graph autoencoders[C]//Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining.New York, USA:ACM Press, 2023:1268-1279.
[28] TOUTANOVA K, CHEN D Q, PANTEL P, et al. Representing text for joint embedding of text and knowledge bases[C]//Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing. Stroudsburg, USA:ACL, 2015:1499-1509.
[29] XIONG W H, HOANG T, WANG W Y. DeepPath:a reinforcement learning method for knowledge graph reasoning[C]//Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing. Stroudsburg, USA:ACL, 2017:564-573.

选择文件类型/文献管理软件名称

选择包含的内容