返回
ComCon: Complementary-Contradictory Regularization for Multimodal Knowledge Graph Completion
DOI:10.1016/j.inffus.2025.104016.png)
摘要
En 中文
• ComCon:利用互补-矛盾特征为MMKGC提出的新型正则化方法。
• 通过约束的多模态特征交互解决模态错位问题。
• 加权负采样(WNS)自适应地减少假阴性影响。
期刊
IF:
15.5
论文数:
4.2K
被引数:
2.7W
机构
引用论文
Open knowledge graph completion with negative-aware representation learning and multi-source reliability inference
INFORMATION FUSION
IF15.5
Contextualized Quaternion Embedding Towards Polysemy in Knowledge Graph for Link Prediction基于知识图谱链接预测的上下文四元数嵌入处理一词多义问题
MvTuckER: Multi-view knowledge graphs representation learning based on tensor tucker modelMvTuckER: 基于张量tucker模型的多视图知识图谱表示学习
INFORMATION FUSION
IF15.5
GS-KGC: A generative subgraph-based framework for knowledge graph completion with large language modelsGS-KGC:一种基于生成子图的框架,用于利用大型语言模型的知识图谱补全
INFORMATION FUSION
IF15.5

