Knowledge Graphs Meet Multi-Modal Learning: A Comprehensive Survey

TL;DR

This comprehensive survey reviews over 300 articles on the intersection of Knowledge Graphs and multi-modal learning, covering construction, tasks, benchmarks, challenges, and emerging trends to guide future research in this evolving field.

Contribution

It provides a detailed overview of KG-aware multi-modal learning and MMKG research, including definitions, task categories, benchmarks, and insights into future directions.

Findings

Identification of key research trajectories in KG4MM and MM4KG

Analysis of evaluation benchmarks for multi-modal tasks

Discussion of emerging trends like large language models and multi-modal pre-training

Abstract

Knowledge Graphs (KGs) play a pivotal role in advancing various AI applications, with the semantic web community's exploration into multi-modal dimensions unlocking new avenues for innovation. In this survey, we carefully review over 300 articles, focusing on KG-aware research in two principal aspects: KG-driven Multi-Modal (KG4MM) learning, where KGs support multi-modal tasks, and Multi-Modal Knowledge Graph (MM4KG), which extends KG studies into the MMKG realm. We begin by defining KGs and MMKGs, then explore their construction progress. Our review includes two primary task categories: KG-aware multi-modal learning tasks, such as Image Classification and Visual Question Answering, and intrinsic MMKG tasks like Multi-modal Knowledge Graph Completion and Entity Alignment, highlighting specific research trajectories. For most of these tasks, we provide definitions, evaluation benchmarks, and additionally outline essential insights for conducting relevant research. Finally, we discuss current challenges and identify emerging trends, such as progress in Large Language Modeling and Multi-modal Pre-training strategies. This survey aims to serve as a comprehensive reference for researchers already involved in or considering delving into KG and multi-modal learning research, offering insights into the evolving landscape of MMKG research and supporting future work.