Knowledge Graphs for Multi-modal Learning: Survey and Perspective

IF 14.7 1区计算机科学 Q1 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE

Information Fusion Pub Date : 2025-03-24 DOI:10.1016/j.inffus.2025.103124

Zhuo Chen , Yichi Zhang , Yin Fang , Yuxia Geng , Lingbing Guo , Jiaoyan Chen , Xiaoze Liu , Jeff Z. Pan , Ningyu Zhang , Huajun Chen , Wen Zhang

引用次数: 0

Abstract

Integrated with multi-modal learning, knowledge graphs (KGs) as structured knowledge repositories, can enhance AI for processing and understanding complex, real-world data. This paper provides a comprehensive survey of cutting-edge research on KG-aware multi-modal learning. For these core areas, we provide task definitions, evaluation benchmarks, and comprehensive insights into key breakthroughs, offering detailed explanations critical for conducting related research. Furthermore, we also discuss current challenges, highlighting emerging trends and future research directions. The repository for this paper can be found at https://github.com/zjukg/KG-MM-Survey.

查看原文本刊更多论文

知识图谱（KG）作为结构化的知识库，与多模态学习相结合，可以提高人工智能处理和理解复杂现实世界数据的能力。本文全面介绍了有关知识图谱感知多模态学习的前沿研究。针对这些核心领域，我们提供了任务定义、评估基准和对关键突破的全面见解，并提供了对开展相关研究至关重要的详细解释。此外，我们还讨论了当前面临的挑战，强调了新兴趋势和未来研究方向。本文的资料库见 https://github.com/zjukg/KG-MM-Survey。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

Information Fusion 工程技术-计算机：理论方法

CiteScore

33.20

自引率

4.30%

发文量

161

审稿时长

7.9 months

期刊介绍： Information Fusion serves as a central platform for showcasing advancements in multi-sensor, multi-source, multi-process information fusion, fostering collaboration among diverse disciplines driving its progress. It is the leading outlet for sharing research and development in this field, focusing on architectures, algorithms, and applications. Papers dealing with fundamental theoretical analyses as well as those demonstrating their application to real-world problems will be welcome.