APKGC: Noise-enhanced Multi-Modal Knowledge Graph Completion with Attention Penalty

Multimodal knowledge graphs (MMKG) store structured world knowledge enriched with multimodal descriptive information. However, MMKG often faces the challenge of incompleteness. The primary objective of multimodal knowledge graph completion (MMKGC) is to predict missing entities within MMKG. Current MMKGC methods struggle with addressing the issue of over-trust attention and how to enhance the robustness of the model. To overcome these problems, we introduce APKGC, a noise-enhanced multimodal method for knowledge graph completion with attention penalty. APKGC effectively adjusts the attention scores in the language model and alleviates over-trust attention through a specifically designed attention penalty module. Additionally, an adaptive noise sampling module is proposed to supplement the entity's multimodal information, thereby enhancing the model's robustness. Experimental evaluation demonstrates that APKGC excels in overcoming these challenges. Compared to the existing state-of-the-art MMKGC model, APKGC improves Hit@1 by 3.3% on the DB15K dataset and by 3.4% on the MKG-W dataset.

Authors

• Yue Jian School of Computer Science, Hubei University, Wuhan 430062, China Hubei Key Laboratory of Big Data Intelligent Analysis and Application (Hubei University), Wuhan 430062, China Key Laboratory of Intelligent Sensing System and Security (Hubei University), Ministry of Education, Wuhan 430062, China
• Xiangyu Luo School of Cyber Science and Technology, Hubei University, Wuhan 430062, China
• Zhifei Li School of Computer Science, Hubei University, Wuhan 430062, China Hubei Key Laboratory of Big Data Intelligent Analysis and Application (Hubei University), Wuhan 430062, China Key Laboratory of Intelligent Sensing System and Security (Hubei University), Ministry of Education, Wuhan 430062, China
• Miao Zhang
• Yan Zhang
• Kui Xiao School of Computer Science, Hubei University, Wuhan 430062, China Hubei Key Laboratory of Big Data Intelligent Analysis and Application (Hubei University), Wuhan 430062, China Key Laboratory of Intelligent Sensing System and Security (Hubei University), Ministry of Education, Wuhan 430062, China
• Xiaoju Hou Institute of Vocational Education, Guangdong Industry Polytechnic University, Guangzhou 510300, China

Keywords

No keywords are indexed for this paper.