Home Research Papers Datasets State of the Art Pricing

Discover, visualize, and connect AI research papers. Explore the latest trends and insights in artificial intelligence research.

Product

Home
Research Papers
About

Support

Contact
Terms of Service
Privacy Policy

© 2026 Papersgraph. All rights reserved.

knowledge-base-6

Multi-modal Knowledge Graph

3260 papers • 126 benchmarks • 313 datasets

Link to A Survey for Multi-modal Knowledge Graphs. Papers integrating Knowledge Graphs (KGs) and Multi-Modal Learning, focusing on 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.

(Image credit: Papersgraph)

Benchmarks

These leaderboards are used to track progress in multi-modal-knowledge-graph-6

Trend

Dataset

Best Model

Actions

No benchmarks available.

Libraries

i

Use these libraries to find multi-modal-knowledge-graph-6 models and implementations

Datasets

MMKG

VirtualHome2KG

Subtasks

No subtasks available.

Most implemented papers

Knowledge Graphs Meet Multi-Modal Learning: A Comprehensive Survey

Jeff Z. Pan, Hua-zeng Chen, Xiang Chen, Xiaoze Liu, Zhuo Chen, Lingbing Guo, Yin Fang, Wen Zhang, Yuxia Geng, Ningyu Zhang, Yichi Zhang, Jiaoyan Chen, Yushan Zhu, Qian Li, Jiaqi Li•Wed Feb 07 2024

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.

82

Content

Introduction Benchmarks Datasets Subtasks Libraries Papers

0

LingYi: Medical Conversational Question Answering System based on Multi-modal Knowledge Graphs

Shizhu He, Bin Sun, Shutao Li, Kang Liu, Jun Zhao, Yixuan Weng, Fei Xia, Bin Li•Tue Apr 19 2022

A medical conversational question answering (CQA) system based on the multi-modal knowledge graph, namely"LingYi", which is designed as a pipeline framework to maintain high flexibility, which is more friendly to provide medical services to patients.

28 0

Multi-modal Siamese Network for Entity Alignment

Liyi Chen, Zhi Li, N. Yuan, Zhefeng Wang, Tong Xu, Han Wu, Enhong Chen•Sat Aug 13 2022

A novel Multi- modal Siamese Network for Entity Alignment (MSNEA) is proposed to align entities in different MMKGs, in which multi-modal knowledge could be comprehensively leveraged by the exploitation of inter-modAL effect.

101 0

Modality-Aware Negative Sampling for Multi-modal Knowledge Graph Embedding

Mingyang Chen, Yichi Zhang, Wen Zhang•Sat Apr 22 2023

Modality-Aware Negative Sampling (MANS) for multi-modal knowledge graph embedding (MMKGE) is proposed to address the mentioned problems and empirical results demonstrate that MANS outperforms existing NS methods.

17 0

AspectMMKG: A Multi-modal Knowledge Graph with Aspect-aware Entities

Yanghua Xiao, Jiaan Wang, Zhixu Li, Jingdan Zhang, Xiaodan Wang•Tue Aug 08 2023

This paper constructs AspectMMKG, the first MMKG with aspect-related images by matching images to different entity aspects, and proposes an aspects-related image retrieval (AIR) model, that aims to correct and expand aspect- related images in Aspect MMRKG.

11 0

MACO: A Modality Adversarial and Contrastive Framework for Modality-missing Multi-modal Knowledge Graph Completion

Zhuo Chen, Yichi Zhang, Wen Zhang•Sat Aug 12 2023

A modality adversarial and contrastive framework (MACO) is proposed to solve the modality-missing problem in MMKGC and could achieve state-of-the-art results and serve as a versatile framework to bolster various MMK GC models.

8 0

Multi-Modal Knowledge Graph Transformer Framework for Multi-Modal Entity Alignment

Lihong Wang, Qian Li, Cheng Ji, Shu Guo, Zhaoji Liang, Jianxin Li•Mon Oct 09 2023

A novel MMEA transformer is proposed, called MoAlign, that hierarchically introduces neighbor features, multi-modal attributes, and entity types to enhance the alignment task and outperforms strong competitors and achieves excellent entity alignment performance.

20 0

Towards Semantic Consistency: Dirichlet Energy Driven Robust Multi-Modal Entity Alignment

Qi Qi, Haifeng Sun, Jianxin Liao, Jingyu Wang, Yuanyi Wang, Jiabo Wang, Wei Tang, Shaoling Sun•Tue Jan 30 2024

DESAlign is proposed, a robust method addressing the over-smoothing caused by semantic inconsistency and interpolating missing semantics using existing modalities using existing modalities, and a training strategy for multi-modal knowledge graph learning based on the proposed generalizable theoretical principle.

21 0

Unleashing the Power of Imbalanced Modality Information for Multi-modal Knowledge Graph Completion

Hua-zeng Chen, Wen Zhang, Yichi Zhang, Zhuo Chen, Lei Liang•Wed Feb 21 2024

Adaptive Multi-modal Fusion and Modality Adversarial Training (AdaMF-MAT) is proposed to unleash the power of imbalanced modality information for MMKGC to achieve new state-of-the-art results on three public MMKGC benchmarks.

24 0

Adding a benchmark result helps the community track progress.

Multi-modal Knowledge Graph | State-of-the-Art