浏览全部资源
扫码关注微信
成都信息工程大学 人工智能学院,四川 成都 610225
闫晨曦(1999-),男,CCF学生会员,成都信息工程大学人工智能学院硕士研究生,研究方向为时序知识图谱推理
武志学。
收稿:2025-03-04,
纸质出版:2026-04-15
移动端阅览
闫晨曦,武志学.融合位置编码的层次图神经网络表示方法[J].软件导刊,2026,25(04):132-139.
YAN Chenxi,WU Zhixue.Hierarchical Graph Neural Network Representation Method with Integrated Positional Encoding[J].Software Guide,2026,25(04):132-139.
闫晨曦,武志学.融合位置编码的层次图神经网络表示方法[J].软件导刊,2026,25(04):132-139. DOI: 10.11907/rjdk.242026.
YAN Chenxi,WU Zhixue.Hierarchical Graph Neural Network Representation Method with Integrated Positional Encoding[J].Software Guide,2026,25(04):132-139. DOI: 10.11907/rjdk.242026.
时序知识图谱(TKG)推理旨在通过观察到的事实预测未来时间戳的事实。然而,大多数现有方法忽略了节点的规范位置信息,限制了图神经网络(GNNs)区分同构节点及图对称性等问题的能力。为此,提出一种融合位置编码的层次图神经网络(HGLS-PE)表示方法以提升节点表示能力。具体而言,为了显式关联不同时间戳的实体,首先将TKG转换成全局图,基于构建的全局图模型,从子图级别对每个时间戳内子图中并发出现的事实进行建模,以捕获其潜在的语义关系,从全局图捕获不同时间戳下实体之间的时间依赖性。此外,在子图和全局图两个层级的学习过程中,将位置编码融入节点的消息传播机制中。该方式能够有效区分不同时刻节点和关系对目标节点表示的影响,从而显著增强模型的区分能力和推理能力。在两个公开TKG数据集上进行了广泛实验,结果证明了HGLS-PE的有效性。
Temporal Knowledge Graph (TKG) reasoning aims to predict future facts based on observed ones. However, most existing methods overlook the normalized positional information of nodes, which limits the ability of Graph Neural Networks (GNNs) to address challenges such as isomorphic nodes and graph symmetry. To tackle these issues, we propose a Hierarchical Relational Graph Neural Network with Structural and Positional Encodings (HGLS-PE) to enhance node representation. Specifically, to explicitly associate entities across different timestamps, we first convert the TKG into a global graph. The proposed model captures the semantic dependencies of concurrent facts within subgraphs at each timestamp and temporal dependencies between entities across timestamps in the global graph. Furthermore, during the learning process at both subgraph and global graph levels, positional encodings are integrated into the message-passing mechanism of nodes. This integration effectively distinguishes the influence of nodes and relations at different timestamps on the target node representation, significantly improving the model’s discriminative and reasoning capabilities. Extensive experiments conducted on two public TKG datasets demonstrate the effectiveness of HGLS-PE.
CAI B , XIANG Y , GAO L X , et al . Temporal knowledge graph completion:a survey [C]// Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence , 2023 : 6545 - 6553 . doi: 10.24963/ijcai.2023/734 http://dx.doi.org/10.24963/ijcai.2023/734
JI S X , PAN S R , 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 . doi: 10.1109/tnnls.2021.3070843 http://dx.doi.org/10.1109/tnnls.2021.3070843
ZHANG W Z , SHEN Y G , LI Y . Drug recommendation algorithm integrating knowledge graph and collaborative filtering [J]. Software Guide , 2023 , 22 ( 8 ): 42 - 47 .
张文卓 , 申艳光 , 李焰 . 融合知识图谱与协同过滤的药品推荐算法 [J]. 软件导刊 , 2023 , 22 ( 8 ): 42 - 47 .
LIU J P , SUN Y G , ZHU Q , et al . Knowledge graph aware pseudo query generation for zero-shot document retrieval [J]. Software Guide , 2024 , 23 ( 11 ): 47 - 52 .
刘军平 , 孙医贵 , 朱强 , 等 . 基于知识图谱的零样本文档检索伪查询生成 [J]. 软件导刊 , 2024 , 23 ( 11 ): 47 - 52 .
ZOU A Q , CHEN Y P . Knowledge graph construction method for tax regulations [J]. Software Guide , 2023 , 22 ( 4 ): 32 - 37 .
邹安琪 , 陈艳平 . 面向税收条例的知识图谱构建方法 [J]. 软件导刊 , 2023 , 22 ( 4 ): 32 - 37 .
YANG F Q , ZHANG Y , ZHAO X C , et al . Unleashing the power of decoders: temporal knowledge graph extrapolation with householder transformation [J]. Symmetry , 2024 , 16 ( 9 ): 1166 . doi: 10.3390/sym16091166 http://dx.doi.org/10.3390/sym16091166
LIU X L , LIU S Q . Improved temporal knowledge graph prediction model based on RE-GCN [J]. Journal of Heilongjiang University of Science and Technology , 2024 , 34 ( 5 ): 812 - 816 .
刘兴丽 , 柳始群 . 基于RE-GCN改进的时序知识图谱预测模型 [J]. 黑龙江科技大学学报 , 2024 , 34 ( 5 ): 812 - 816 .
CHEN J , ZHAO X C , SUI J Y , et al . Story-inspired large language models for temporal knowledge graph prediction [J]. Pattern Recognition and Artificial Intelligence , 2024 , 37 ( 8 ): 715 - 728 .
陈娟 , 赵新潮 , 隋京言 , 等 . 故事启发大语言模型的时序知识图谱预测 [J]. 模式识别与人工智能 , 2024 , 37 ( 8 ): 715 - 728 .
LI Z X , GUAN S P , JIN X L , et al . Two-stage temporal knowledge graph inference based on multi-historical sequence joint evolution modeling [J]. Journal of Chinese Information Processing , 2024 , 38 ( 2 ): 46 - 53 .
李紫宣 , 官赛萍 , 靳小龙 , 等 . 基于多历史序列联合演化建模的两阶段时序知识图谱推理 [J]. 中文信息学报 , 2024 , 38 ( 2 ): 46 - 53 .
LI Z X , GUAN S P , JIN X L , et al . Complex evolutional pattern learning for temporal knowledge graph reasoning [C]// Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics , 2022 : 290 - 296 . doi: 10.18653/v1/2022.acl-short.32 http://dx.doi.org/10.18653/v1/2022.acl-short.32
XU Y , OU J J , XU H , et al . Temporal knowledge graph reasoning with historical contrastive learning [C]// Proceedings of the Thirty-Seventh AAAI Conference on Artificial Intelligence and Thirty-Fifth Conference on Innovative Applications of Artificial Intelligence and Thirteenth Symposium on Educational Advances in Artificial Intelligence , 2023 : 4765 - 4773 . doi: 10.1609/aaai.v37i4.25601 http://dx.doi.org/10.1609/aaai.v37i4.25601
SHEN Y H , JIANG X H , WANG Y Z , et al . A survey on inference in temporal knowledge graphs [J]. Chinese Journal of Computers , 2023 , 46 ( 6 ): 1272 - 1301 .
沈英汉 , 江旭晖 , 王元卓 , 等 . 时态知识图谱的推理研究综述 [J]. 计算机学报 , 2023 , 46 ( 6 ): 1272 - 1301 .
WANG Y H , CHEN Z Y , ZHAO X , et al . Research progress and trend of temporal knowledge graph representation and reasoning [J]. Journal of Software , 2024 , 35 ( 8 ): 3923 - 3951 .
王俞涵 , 陈子阳 , 赵翔 , 等 . 时序知识图谱表示与推理的研究进展与趋势 [J]. 软件学报 , 2024 , 35 ( 8 ): 3923 - 3951 .
ZHANG M Q , XIA Y W , LIU Q , et al . Learning latent relations for temporal knowledge graph reasoning [C]// Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics , 2023 : 12617 - 12631 . doi: 10.18653/v1/2023.acl-long.705 http://dx.doi.org/10.18653/v1/2023.acl-long.705
LIU Z X , HOU Z N , GUAN S P , et al . HiSMatch: historical structure matching based temporal knowledge graph reasoning [C]// Findings of the Association for Computational Linguistics:EMNLP 2022 , 2022 : 7328 - 7338 .
LIANG K , MENG L Y , LIU M , et al . Learn from relational correlations and periodic events for temporal knowledge graph reasoning [C]// Proceedings of the 46th International ACM SIGIR Conference on Research and Development in Information Retrieva , 2023 : 1559 - 1568 . doi: 10.1145/3539618.3591711 http://dx.doi.org/10.1145/3539618.3591711
ZHANG C K , MA H D . Temporal knowledge graph inference based on joint convolution [J]. Computer Engineering and Applications , 2025 , 61 ( 18 ): 166 - 174 .
张成珅 , 马汉达 . 基于联合卷积的时序知识图谱推理 [J]. 计算机工程与应用 , 2025 , 61 ( 18 ): 166 - 174 .
LIU W , XIE L J , ZHANG Z H , et al . Temporal knowledge graph inference based on tensor decomposition embedding [J]. Journal of Beijing Information Science & Technology University , 2024 , 39 ( 1 ): 49 - 54 .
刘伟 , 谢璐钧 , 张智慧 , 等 . 基于张量分解嵌入的时序知识图谱推理 [J]. 北京信息科技大学学报 , 2024 , 39 ( 1 ): 49 - 54 .
ZHOU G Y , LI P F , XIE P H , et al . Temporal knowledge graph inference based on diffusion probability distribution [J]. Journal of Software , 2024 , 35 ( 11 ): 5083 - 5097 .
周光有 , 李鹏飞 , 谢鹏辉 , 等 . 基于扩散概率分布的时序知识图谱推理 [J]. 软件学报 , 2024 , 35 ( 11 ): 5083 - 5097 .
DONG H , WANG P Y , XIAO M , et al . Temporal inductive path neural network for temporal knowledge graph reasoning [J]. Artificial Intelligence , 2024 , 329 : 104085 . doi: 10.1016/j.artint.2024.104085 http://dx.doi.org/10.1016/j.artint.2024.104085
ZHU C C , CHEN M H , FAN C J , et al . Learning from history: modeling temporal knowledge graphs with sequential copy-generation networks [C]// Proceedings of the AAAI Conference on Artificial Intelligence , 2021 : 4732 - 4740 . doi: 10.1609/aaai.v35i5.16604 http://dx.doi.org/10.1609/aaai.v35i5.16604
LIU Z T , TAN L , LI M F , et al . SiMFy: a simple yet effective approach for temporal knowledge graph reasoning [C]// Findings of the Association for Computational Linguistics: EMNLP 2023 , 2023 : 3825 - 3836 . doi: 10.18653/v1/2023.findings-emnlp.249 http://dx.doi.org/10.18653/v1/2023.findings-emnlp.249
JIN W , QU M , JIN X S , et al . Recurrent event network: autoregressive structure inference over temporal knowledge graphs [C]// Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing , 2020 : 6669 - 6683 . doi: 10.18653/v1/2020.emnlp-main.541 http://dx.doi.org/10.18653/v1/2020.emnlp-main.541
ELMAN J L . Finding structure in time [J]. Cognitive Science , 1990 , 14 ( 2 ): 179 - 211 . doi: 10.1207/s15516709cog1402_1 http://dx.doi.org/10.1207/s15516709cog1402_1
LI Z X , JIN X L , LI W , et al . Temporal knowledge graph reasoning based on evolutional representation learning [C]// Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval , 2021 : 408 - 417 . doi: 10.1145/3404835.3462963 http://dx.doi.org/10.1145/3404835.3462963
ZHANG M Q , XIA Y W , LIU Q , et al . Learning long-and short-term representations for temporal knowledge graph reasoning [C]// Proceedings of the ACM Web Conference 2023 , 2023 : 2412 - 2422 . doi: 10.1145/3543507.3583242 http://dx.doi.org/10.1145/3543507.3583242
CHUNG J , GULCEHRE C , CHO K , et al . Empirical evaluation of gated recurrent neural networks on sequence modeling[DB/OL] . https://arxiv.org/pdf/1412.3555 https://arxiv.org/pdf/1412.3555 .
VASWANI A , SHAZEER N , PARMAR N , et al . Attention is all you need [C]// Proceedings of the 31st International Conference on Neural Information Processing Systems , 2017 : 6000 - 6010 .
DWIVEDI V P , LUU A T , LAURENT T , et al . Graph neural networks with learnable structural and positional representations[DB/OL] . https://arxiv.org/pdf/2110.07875 https://arxiv.org/pdf/2110.07875 .
RAMPÁŠEK L , GALKIN M , DWIVEDI V P , et al . Recipe for a general, powerful, scalable graph transformer [C]// Proceedings of the 36th International Conference on Neural Information Processing Systems , 2022 : 14501 - 14515 . doi: 10.52202/068431-1054 http://dx.doi.org/10.52202/068431-1054
SHANG C , TANG Y , HUANG J , et al . End-to-end structure-aware convolutional networks for knowledge base completion [C]// Proceedings of the Thirty-Third AAAI Conference on Artificial Intelligence and Thirty-First Innovative Applications of Artificial Intelligence Conference and Ninth AAAI Symposium on Educational Advances in Artificial Intelligence , 2019 : 3060 - 3067 . doi: 10.1609/aaai.v33i01.33013060 http://dx.doi.org/10.1609/aaai.v33i01.33013060
SUN H H , ZHONG J L , MA Y P , et al . TimeTraveler: reinforcement learning for temporal knowledge graph forecasting [C]// Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing , 2021 : 8306 - 8319 . doi: 10.18653/v1/2021.emnlp-main.655 http://dx.doi.org/10.18653/v1/2021.emnlp-main.655
0
浏览量
1
下载量
0
CSCD
关联资源
相关文章
相关作者
相关机构
鄂公网安备42010602004949号