改进半监督学习的知识图谱节点分类模型

An Improved Semi-supervised Learning Model for Knowledge Graph Node Classification

摘要

针对知识图谱节点分类中语义信息和图结构信息协同建模不足,以及有限标注条件下多层特征利用不充分的问题,提出一种基于半监督学习的图卷积和注意力跳跃网络模型.该模型利用图卷积网络提取结构特征,通过图注意力网络自适应聚合邻域信息,并结合长短期记忆网络和注意力机制融合不同层次的节点表示.在开放图基准中的计算机科学论文引用网络数据集上的实验结果表明:该模型的准确率、精确率、召回率以及精确率和召回率的调和平均值分别为75.96%,73.52%,72.34%和72.93%,优于目前多种主流图神经网络模型;该模型能有效融合节点语义、图结构与跨层特征,提升有限标注条件下的节点分类性能.

Abstract

To address the issuse of the insufficient collaborative modeling of semantic and structural information and the inadequate utilization of multilayer features in knowledge graph node classification with limited labels, a semi-supervised graph convolutional and attention-based jump network is proposed in this paper. The model employs a graph convolutional network to extract structural features, a graph attention network to adaptively aggregate neighborhood information, and a long short-term memory network combined with an attention mechanism to fuse node representations from different layers. Experimental results on the computer science paper citation network dataset in the open graph benchmark demonstrate that the model achieves an accuracy of 75.96%, a precision of 73.52%, a recall of 72.34%, and a harmonic mean of precision and recall of 72.93%, which outperforms several mainstream graph neural network models. The results demonstrate that the proposed model effectively integrates node semantics, graph structures, and cross-layer features, thereby improving the performance of node classification under limited supervision.

关键词

知识图谱 / 图卷积网络 / 图注意力机制 / 跳跃连接机制 / 半监督学习

Key words

knowledge graph / graph convolutional network / graph attention mechanism / jumping knowledge mechanism / semi-supervised learning

参考文献

[1] 闫树, 魏凯, 洪万福. 知识图谱技术与应用[M]. 北京: 人民邮电出版社, 2019:104.

[2] (Yan S, Wei K, Hong W F. Knowledge Graph Technology and Applications[M]. Beijing: Posts & Telecom Press, 2019: 104.)

[3] 冯钧, 朱跃龙, 杭婷婷, 等. 知识图谱研究与领域实践[M]. 北京: 人民邮电出版社, 2022:284.

[4] (Feng J, Zhu Y L, Hang T T, et al. Research and Domain Practice of Knowledge Graphs[M]. Beijing: Posts & Telecom Press, 2022: 284.)

[5] Wang Q, Mao Z D, Wang B, et al. Knowledge Graph Embedding: A Survey of Approaches and Applications[J]. IEEE Transactions on Knowledge and Data Engineering, 2017, 29(12): 2724-2743.

[6] 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.

[7] Nickel M, Murphy K, Tresp V, et al. A Review of Relational Machine Learning for Knowledge Graphs[J]. Proceedings of the IEEE, 2016, 104(1): 11-33.

[8] Chen X J, Jia S B, Xiang Y. A Review: Knowledge Reasoning over Knowledge Graph[J]. Expert Systems with Applications, 2020, 141: 112948-1-112948-13.

[9] Szummer M, Jaakkola T. Partially Labeled Classification with Markov Random Walks[C]// Advances in Neural Information Processing Systems. Cambridge, MA: MIT Press, 2002: 945-952.

[10] 孙忠. 基于文本的知识图谱实体分类方法研究[D]. 上海: 东华大学, 2022.

[11] (Sun Z. Research on Text-Based Knowledge Graph Entity Classification Methods[D]. Shanghai: Donghua University, 2022.)

[12] Kipf T N, Welling M. Semi-supervised Classification with Graph Convolutional Networks[EB/OL]. (2016-09-09)[2025-05-01]. https://arxiv.org/abs/1609.02097.

[13] Yao L, Mao C S, Luo Y. Graph Convolutional Networks for Text Classification[C]// Proceedings of the AAAI Conference on Artificial Intelligence. Palo Alto: AAAI Press, 2019: 7370-7377.

[14] Schlichtkrull M, Kipf T N, Bloem P, et al. Modeling Relational Data with Graph Convolutional Networks[C]// The Semantic Web: ESWC 2018. Berlin: Springer, 2018: 593-607.

[15] Veličković P, Curull G, Casanova A, et al. Graph Attention Networks[EB/OL]. (2017-10-30)[2025-04-20]. https://arxiv.org/abs/1700.10903.

[16] Wang X, He X N, Cao Y X, et al. KGAT: Knowledge Graph Attention Network for Recommendation[C]// Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. New York: ACM, 2019: 950-958.

[17] Gasteiger J, Bojchevski A, Günnemann S. Predict Then Propagate: Graph Neural Networks Meet Personalized PageRank[EB/OL]. (2018-10-14)[2025-05-10]. https://arxiv.org/abs/1810.05997.

[18] Chien E, Peng J H, Li P, et al. Adaptive Universal Generalized PageRank Graph Neural Network[EB/OL]. (2020-06-14)[2025-05-21]. https://arxiv.org/abs/2006.07988.

[19] Xu K Y L, Li C T, Tian Y L, et al. Representation Learning on Graphs with Jumping Knowledge Networks[C]// Proceedings of the 35th International Conference on Machine Learning. [S. l.]: PMLR, 2018: 5453-5462.

[20] Li R L, Wang C, Shang R H, et al. Node Classification Based on Structure Migration and Graph Attention Convolutional Crossover Network[J]. Knowledge-Based Systems, 2025, 309: 112813-1-112813-21.

[21] Zhai X, Oliver A, Kolesnikov A, et al. S4L: Self-supervised Semi-supervised Learning[C]// Proceedings of the IEEE/CVF International Conference on Computer Vision. Piscataway, NJ: IEEE, 2019: 1476-1485.

[22] Krishnapuram B, Williams D, Xue Y, et al. On Semi-supervised Classification[C]// Advances in Neural Information Processing Systems. Cambridge, MA: MIT Press, 2005: 721-728.

[23] Liu Y H, Huang L, Giunchiglia F, et al. Improved Graph Contrastive Learning for Short Text Classification[C]// Proceedings of the AAAI Conference on Artificial Intelligence. Palo Alto: AAAI Press, 2024: 18716-18724.

[24] Chapelle O, Zien A. Semi-supervised Classification by Low Density Separation[C]// Proceedings of the Tenth International Workshop on Artificial Intelligence and Statistics. [S. l.]: PMLR, 2005: 57-64.

[25] Wen X Y, Li W B. Time Series Prediction Based on LSTM-Attention-LSTM Model[J]. IEEE Access, 2023, 11: 48322-48331.

[26] Hu W H, Fey M, Zitnik M, et al. Open Graph Benchmark: Datasets for Machine Learning on Graphs[EB/OL]. (2020-05-02)[2025-04-30]. https://arxiv.org/abs/2005.00687.

[27] Church K W. Word2Vec[J]. Natural Language Engineering, 2017, 23(1): 155-162.

[28] Mikolov T, Sutskever I, Chen K, et al. Distributed Representations of Words and Phrases and Their Compositionality[C]// Advances in Neural Information Processing Systems. New York: ACM, 2013: 3111-3119.

[29] Kingma D P, Ba J. Adam: A Method for Stochastic Optimization[EB/OL]. (2014-12-22)[2025-05-11]. https://arxiv.org/abs/1412.6980.

[30] Hamilton W L, Ying Z, Leskovec J. Inductive Representation Learning on Large Graphs[C]// Advances in Neural Information Processing Systems. New York: ACM, 2017: 1024-1034.

基金资助

国家自然科学基金(62261056)

教育部产学合作协调育人项目(231107173102719)

云南省媒体融合重点实验室开放项目(220245203)