Commonsense Knowledge Graph Completion Method Based on Relation-Constrained Contrastive Learning

doi:10.19678/j.issn.1000-3428.0069984

Abstract

Abstract:

Knowledge graph completion aims to address the problems of knowledge deficiency and incompleteness, by predicting missing entities or relationships in a knowledge graph. Compared to traditional knowledge graphs, commonsense knowledge graphs are typically sparser, making them insufficient for representing entities solely based on structural information. Therefore, some studies enrich commonsense knowledge graphs by utilizing semantic representations in addition to structural information. However, these methods typically focus only on the semantic representation of individual entities and ignore the semantic associations between entity sets. To address this issue, this study proposes a new method called relation-constrained contrastive learning for common-sense knowledge graph completion. First, the method uses relations to divide entities into different sets and selects positive and negative sample pairs from these sets for contrastive learning, to obtain the basic representations of the entities. It further learns comprehensive entity representations by constraining the similarity between individual entity semantic representations and the central representations of the sets to which the entities belong. The completion task is performed based on these comprehensive representations. Experiments on two public datasets show that the proposed model outperforms baseline models. Compared to the second-best model, CPNC, the proposed model improves the Mean Reciprocal Rank (MRR) by 1.09 and 2.48 percentage points and Hits@1 by 1.02 and 1.55 percentage points on the CN-100K and ATOMIC datasets, respectively.

Key words: commonsense knowledge graph, knowledge graph completion, contrastive learning, relation constraint, semantic representation

摘要：

知识图谱补全旨在通过预测知识图谱中缺失的实体或关系来解决知识缺失和不完整问题。与传统知识图谱相比, 常识知识图谱通常更加稀疏, 因此仅依靠结构信息来表征实体往往存在不足。为此, 现有研究在结构信息的基础上, 利用语义表征来丰富常识知识图谱, 但这些方法通常只关注单个实体的语义表征, 而忽视了实体集合的语义关联。针对该问题, 提出一种基于关系约束对比学习的常识知识图谱补全方法。首先, 利用关系将实体划分为不同的集合, 从集合中挑选正负样本对进行对比学习, 以获取实体的基础表征; 在此基础上, 以实体个体语义表征和实体所在集合中心表征之间的相似性为约束, 进一步学习实体的综合表征, 并基于该综合表征完成补全任务。在两个公共数据集CN-100K和ATOMIC上进行了实验, 结果表明该模型相比基线模型具有更优的性能: 相比次优模型CPNC, 该模型在两个数据集上平均倒数排名(MRR)值分别提升了1.09和2.48百分点, Hits@1值分别提升了1.02和1.55百分点。

关键词: 常识知识图谱, 知识图谱补全, 对比学习, 关系约束, 语义表征

HE Hongguang, XIAN Yantuan, XIANG Yan. Commonsense Knowledge Graph Completion Method Based on Relation-Constrained Contrastive Learning[J]. Computer Engineering, 2026, 52(4): 122-130.

和红光, 线岩团, 相艳. 基于关系约束对比学习的常识知识图谱补全方法[J]. 计算机工程, 2026, 52(4): 122-130.

/ Recommend / Download Citations

URL: https://www.ecice06.com/EN/10.19678/j.issn.1000-3428.0069984

https://www.ecice06.com/EN/Y2026/V52/I4/122

Figures/Tables 8

Fig.1 RCCL-CSKGC model framework

Fig.2 Results of different positive and negative sample ratios in CN-100K

Fig.3 Results of different positive and negative sample ratios in ATOMIC

Fig.4 The impact of different numbers of clusters

Fig.5 The impact of weight α on experimental results

References 30

1	符家成, 田瑾, 张玉金, 等. 结合前置三元组集的知识图谱推荐. 计算机工程, 2025, 51(9): 101- 109. doi: 10.19678/j.issn.1000-3428.0068953
	FU J C, TIAN J, ZHANG Y J, et al. Knowledge graph recommendation based on previous triple set. Computer Engineering, 2025, 51(9): 101- 109. doi: 10.19678/j.issn.1000-3428.0068953
2	陈跃鹤, 贾永辉, 谈川源, 等. 基于知识图谱全局和局部特征的复杂问答方法. 软件学报, 2023, 34(12): 5614- 5628.
	CHEN Y H, JIA Y H, TAN C Y, et al. Method for complex question answering based on global and local features of knowledge graph. Journal of Software, 2023, 34(12): 5614- 5628.
3	马恒志, 钱育蓉, 冷洪勇, 等. 知识图谱嵌入研究进展综述. 计算机工程, 2025, 51(2): 18- 34. doi: 10.19678/j.issn.1000-3428.0068386
	MA H Z, QIAN Y R, LENG H Y, et al. Review of research progress on knowledge graph embedding. Computer Engineering, 2025, 51(2): 18- 34. doi: 10.19678/j.issn.1000-3428.0068386
4	KURT B, COLIN E, PRAVEEN 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, USA: ACM Press, 2008: 1247-1250.
5	DENNY V, MARKUS K. Wikidata: a free collaborative knowledgebase. Communications of the ACM, 2014, 57(10): 78- 85. doi: 10.1145/2629489
6	SUCHANEK F M, KASNECI G, WEIKUM G. YAGO: a core of semantic knowledge[C]//Proceedings of the 16th International Conference on World Wide Web. New York, USA: ACM Press, 2007: 697-706.
7	SPEER R, CHIN J, HAVASI C. ConceptNet 5.5: an open multilingual graph of general knowledge[C]//Proceedings of the AAAI Conference on Artificial Intelligence. [S. l. ]: AAAI, 2017: 1-9.
8	SAP M, BRAS R, ALLAWAY E, et al. ATOMIC: an atlas of machine commonsense for if-then reasoning[C]//Proceedings of the AAAI Conference on Artificial Intelligence. [S. l. ]: AAAI, 2019: 3027-3035.
9	BORDES A, USUNIER N, GARCIA-DURAN A, et al. Translating embeddings for modeling multi-relational data. Advances in Neural Information Processing Systems, 2013, 26, 1- 10.
10	SUN Z Q, DENG Z H, NI J Y, et al. Rotate: knowledge graph embedding by relational rotation in complex space[C]//Proceedings of the 7th International Conference on Learning Representations. New Orleans, USA: [s. n. ], 2019: 1-10.
11	TROUILLON T, WELBL J, RIEDEL S, et al. Complex embeddings for simple link prediction[C]//Proceedings of International Conference on Machine Learning. [S. l. ]: PMLR, 2016: 2071-2080.
12	DETTMERS T, MINERVINI P, STENETORP P, et al. Convolutional 2D knowledge graph embeddings[C]//Proceedings of the AAAI Conference on Artificial Intelligence. [S. l. ]: AAAI, 2018: 1-10.
13	SCHLICHTKRULL M, KIPF T N, BLOEM P, et al. Modeling relational data with graph convolutional networks[C]//Proceedings of the 15th International Conference on Semantic Web. Berlin, Germany: Springer International Publishing, 2018: 593-607.
14	MALAVIYA C, BHAGAVATULA C, BOSSELUT A, et al. Commonsense knowledge base completion with structural and semantic context[C]//Proceedings of the AAAI Conference on Artificial Intelligence. [S. l. ]: AAAI Press, 2020: 34(3): 2925-2933.
15	WANG B, WANG G T, HUANG J, et al. Inductive learning on commonsense knowledge graph completion[C]//Proceedings of the International Joint Conference on Neural Networks (IJCNN). Washington D. C., USA: IEEE Press, 2021: 1-8.
16	WU S W, SHEN X Q, XIA R. Commonsense knowledge graph completion via contrastive pretraining and node clustering[C]//Proceedings of the Findings of the Association for Computational Linguistics: ACL 2023. Stroudsburg, USA: ACL, 2023: 13977-13989.
17	DEVLIN J, CHANG M W, LEE K, et al. BERT: pre-training of deep bidirectional Transformers for language understanding[C]// Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers). [S. l. ]: ACL, 2019: 4171-4186.
18	YANG B S, YIH W, HE X D, et al. Embedding entities and relations for learning and inference in knowledge bases[EB/OL]. [2024-05-11]. https://arxiv.org/abs/1412.6575.
19	SHANG C, TANG Y, HUANG J, et al. End-to-end structure-aware convolutional networks for knowledge base completion[C]// Proceedings of the AAAI Conference on Artificial Intelligence. [S. l. ]: AAAI Press, 2019: 3060-3067.
20	ZEB A, SAIF S, CHEN J D, et al. Complex graph convolutional network for link prediction in knowledge graphs. Expert Systems with Applications, 2022, 200, 116796. doi: 10.1016/j.eswa.2022.116796
21	XU Z Z, YE P, CHEN H, et al. Ruleformer: context-aware rule mining over knowledge graph[EB/OL]. [2024-05-11]. https://arxiv.org/pdf/2209.05815.
22	HAN C, HE Q Z, YU C, et al. Logical entity representation in knowledge-graphs for differentiable rule learning[EB/OL]. [2024-05-11]. https://arxiv.org/pdf/2305.12738.
23	LV X, LIN Y K, CAO Y X, et al. Do pre-trained models benefit knowledge graph completion?A reliable evaluation and a reasonable approach[C]//Proceedings of the Findings of the Association for Computational Linguistics: ACL 2022. Stroudsburg, USA: ACL, 2022: 3570-3581.
24	WANG L, ZHAO W, WEI Z Y, 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 (Volume 1: Long Papers). Stroudsburg, USA: ACL, 2022: 4281-4294.
25	LI X, TAHERI A, TU L F, et al. Commonsense knowledge base completion[C]//Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). Stroudsburg, USA: ACL, 2016: 1445-1455.
26	BOSSELUT A, RASHKIN H, SAP M, et al. COMET: commonsense transformers for automatic knowledge graph construction[C]//Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics. Stroudsburg, USA: ACL, 2019: 4762-4779.
27	SHEN X Q, WU S W, XIA R. Dense-ATOMIC: towards densely-connected ATOMIC with high knowledge coverage and massive multi-hop paths[C]//Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). Stroudsburg, USA: ACL, 2023: 13292-13305.
28	JU J H, YANG D Q, LIU J P. Commonsense knowledge base completion with relational graph attention network and pre-trained language model[C]//Proceedings of the 31st ACM International Conference on Information and Knowledge Management. New York, USA: ACM Press, 2022: 4104-4108.
29	SU Y, WANG Z H, FANG T Q, et al. MICO: a multi-alternative contrastive learning framework for commonsense knowledge representation[C]//Proceedings of the Findings of the Association for Computational Linguistics: EMNLP 2022. Stroudsburg, USA: ACL, 2022: 1339-1351.
30	PAN Y D, LIU J, ZHAO T Z, et al. Context-aware commonsense knowledge graph reasoning with path-guided explanations. IEEE Transactions on Knowledge and Data Engineering, 2024, 36(8): 3725- 3738. doi: 10.1109/TKDE.2024.3365103

[1]	ZHANG Zhen, YOU Lan, PENG Qingxi, JIN Hong, ZENG Haoqiu, XIA Yuchun. XSGCL: A Lightweight Graph Contrastive Learning Framework for Recommendation [J]. Computer Engineering, 2026, 52(4): 163-175.
[2]	GUO Tiansheng, XIE Jinkui. Adaptive Adjustment Graph Augmentation and Representation Structures for Recommendation Model [J]. Computer Engineering, 2026, 52(2): 69-78.
[3]	LI Qiang, TAN Xingyi, ZHENG Wei, LIU Zhen, YANG Wenhai. Graph Neural Network Inference Optimization Based on Adversarial Training and Contrastive Representation Distillation [J]. Computer Engineering, 2026, 52(1): 126-135.
[4]	YU Peng, YANG Jiaqi, CHEN Xinran, HE Chaobo. Feature-enhanced Recommendation Algorithm Based on Bipartite Graph Contrastive Learning [J]. Computer Engineering, 2025, 51(7): 100-110.
[5]	YAO Xun, WANG Haipeng, HU Xinrong, YANG Jie. Multi-view Contrastive Recommendation Algorithm Based on Adaptive Enhancement [J]. Computer Engineering, 2025, 51(5): 103-113.
[6]	LIU Chunyu, CHEN Qingfeng, MO Shaocong, XIE Ze. Knowledge Graph Completion Based on Logical Rules and Graph Neural Network [J]. Computer Engineering, 2025, 51(3): 131-143.
[7]	QIAN Lifeng, LI Jing, ZOU Xuxi, CHEN Yu, GU Yalin, WEI Xunhu. Multi-view Graph Clustering Algorithm Based on Dual Contrastive Learning and Hard Sample Mining [J]. Computer Engineering, 2025, 51(12): 82-95.
[8]	Shuang GAO, Yilun SHI, Qiaozhi XU, Lei YU. Research on Cardiac MRI Segmentation Based on Asymmetric Encoding and Decoding Structure of Contrastive Learning [J]. Computer Engineering, 2024, 50(8): 290-300.
[9]	Lai QIAN, Weiwei ZHAO. Text Classification Method Based on Contrastive Learning and Attention Mechanism [J]. Computer Engineering, 2024, 50(7): 104-111.
[10]	Juan LIU, Youxiang DUAN, Yuxi LU, Lu ZHANG. Knowledge Graph Completion with Knowledge Enhancement and Contrastive Learning [J]. Computer Engineering, 2024, 50(7): 112-122.
[11]	WU Xing, YIN Haoyu, YAO Junfeng, LI Weimin, QIAN Quan. Multimodal Sentiment Analysis for Video Data [J]. Computer Engineering, 2024, 50(6): 218-227.
[12]	ZHANG Baoxin, YANG Dan, NIE Tiezheng, KOU Yue. Recommendation Method Based on Self-supervised Multi-view Graph Collaborative Filtering [J]. Computer Engineering, 2024, 50(5): 100-110.
[13]	LI Tianfang, PU Yuanyuan, ZHAO Zhengpeng, XU Dan, QIAN Wenhua. Image-to-Image Translation Based on CLIP and Dual-Spatially Adaptive Normalization [J]. Computer Engineering, 2024, 50(5): 229-240.
[14]	ZHANG Hongchen, LI Linyu, YANG Li, SAN Chenjun, YIN Chunlin, YAN Bing, YU Hong, ZHANG Xuan. Knowledge Graph Completion Based on Contrastive Learning and Language Model-Enhanced Embedding [J]. Computer Engineering, 2024, 50(4): 168-176.
[15]	LI Zhengxue, LI Zhiming, PENG Dezhong, CHEN Jie. User Classification of Social Networks Based on Feature Contrastive Learning and Graph Convolution [J]. Computer Engineering, 2024, 50(4): 258-266.

Please choose a citation manager

Content to export