Journal of Frontiers of Computer Science and Technology
• Science Researches • Next Articles
YE Zhihong, WU Yunbing, DAI Sichong1, ZENG Zhihong
叶志鸿, 吴运兵, 戴思翀, 曾智宏
Abstract: Knowledge graph completion aims to expand and enhance knowledge graphs by predicting missing triples. Multi-modal knowledge graph completion integrates entity ontology information such as entity descriptions, entity images, and entity attributes to obtain more accurate entity representations. Existing research projects different modalities into a unified space to obtain joint representations of entities, then combine knowledge graph structural information for predictions. However, existing methods have difficulty capturing the complex interactions between entity background knowledge when fusing multi-modal information, which inevitably leads to information loss and insufficient feature extraction capabilities; overfitting and limited entity relation interactions restrict the performance of 2D convolution models, making it difficult to integrate knowledge graph structural information. Therefore, this paper used a multi-level fusion knowledge graph completion model. To fully integrate entity multimodal information, three different fusion methods are simultaneously used, along with joint decision learning, aiming to combine the complementary information provided by different multi-modal fusion methods to obtain rich and diverse entity representations. To fully integrate knowledge graph structural information, feature generalization is proposed to alleviate the overfitting issues of 2D convolution models, combined with feature reshaping to enhance interactions between entities and relations. Experiments on multiple public datasets demonstrate the superior performance of the proposed method.
Key words: knowledge graph completion, multi-model fusion, ontology information, structural information, decision learning
摘要: 知识图谱补全旨在通过预测缺失的三元组来扩展和完善知识图谱,多模态知识图谱补全融合了实体的本体信息,如实体描述、实体图像和实体属性,以获取更精确的实体表示。现有研究将不同模态投影到统一的空间中,以获取实体模态联合表示,再融合知识图谱结构信息做出预测。然而,现存方法融合多模态信息时难以捕捉实体背景知识的复杂交互,不可避免地存在信息丢失和特征提取能力不足的问题;同时过拟合及实体关系交互不足限制了二维卷积模型性能,导致难以融合知识图谱结构信息。因此,本文提出了多级融合知识图谱补全模型。为充分融合实体多模态信息,提出同时使用三种不同融合方法,并联合决策学习,旨在结合不同多模态融合方法提供的互补信息,以获取实体丰富多样的表示;为充分融合知识图谱结构信息,利用特征泛化来缓解二维卷积模型的过拟合问题,并结合特征重塑增强实体与关系间交互。实验结果表明,本文模型在多个公开数据集上均取得较好性能。
关键词: 知识图谱补全, 多模态融合, 本体信息, 结构信息, 决策学习
YE Zhihong, WU Yunbing, DAI Sichong, ZENG Zhihong. The Multi-level Fusion Knowledge Graph Completion Model[J]. Journal of Frontiers of Computer Science and Technology, DOI: 10.3778/j.issn.1673-9418.2404032.
叶志鸿, 吴运兵, 戴思翀, 曾智宏. 多级融合知识图谱补全模型[J]. 计算机科学与探索, DOI: 10.3778/j.issn.1673-9418.2404032.
0 / Recommend
Add to citation manager EndNote|Ris|BibTeX
URL: http://fcst.ceaj.org/EN/10.3778/j.issn.1673-9418.2404032
/D:/magtech/JO/Jwk3_kxyts/WEB-INF/classes/