arrow
Return

MOUNT: Modality bottlenecked knowledge graph completion with multiple guidance exploitation

delete2026-01-19
delete0
PRE
AI
J
Jinlan Kong
赫晓慧 (Xiaohui He)
H
Haichuan Fang
李盼乐 cover
李盼乐 (Panle Li)
乔梦佳 (Mengjia Qiao)
X
Xijie Cheng
H
Haofei Li
H
Huitong Feng
H
Haonan Sun
J
Jiandong Shang
DOI:10.1016/j.eswa.2026.131174delete
deleteOriginal
deleteOriginal request for help
deleteShare
deleteSave
Abstract

Abstract

En 中文
• Propose a novel MKGC method based on Variational Information Bottleneck. • Alleviate both intra-modal and inter-modal redundancy via three guidance mechanisms. • Achieve outstanding MKGC performance and exhibit excellent robustness.

Journal

Expert Systems with Applications cover
Expert Systems with Applications
IF:
7.5
Papers:
2.9W
Citations:
10.2W

Organization

N
national supercomputing center
Scholars:
19
Papers: 13
Citations: 0
Z
zhengzhou university
Scholars:
1.1W
Papers: 3.1K
Citations: 2