Learning on Multimodal Graphs: A Survey

TL;DR

This survey reviews the rapidly growing field of multimodal graph learning, analyzing various techniques, applications, and future directions to serve as a foundational resource for researchers in the domain.

Contribution

It provides a comprehensive comparative analysis of existing multimodal graph learning methods, highlighting their characteristics and application scenarios.

Findings

Diverse graph data types and modalities are effectively integrated.

Various learning techniques are characterized and compared.

Key applications across domains are identified and discussed.

Abstract

Multimodal data pervades various domains, including healthcare, social media, and transportation, where multimodal graphs play a pivotal role. Machine learning on multimodal graphs, referred to as multimodal graph learning (MGL), is essential for successful artificial intelligence (AI) applications. The burgeoning research in this field encompasses diverse graph data types and modalities, learning techniques, and application scenarios. This survey paper conducts a comparative analysis of existing works in multimodal graph learning, elucidating how multimodal learning is achieved across different graph types and exploring the characteristics of prevalent learning techniques. Additionally, we delineate significant applications of multimodal graph learning and offer insights into future directions in this domain. Consequently, this paper serves as a foundational resource for researchers seeking to comprehend existing MGL techniques and their applicability across diverse scenarios.