ME3A: A Multimodal Entity Entailment framework for multimodal Entity Alignment

Y Zhao, Y Zhang, X Sui, X Cai - Information Processing & Management, 2025 - Elsevier
Current methods for multimodal entity alignment (MEA) primarily rely on entity
representation learning, which undermines entity alignment performance because of cross …

Relational message passing with mutual information maximization for inductive link prediction

X Liang, G Si, J Li, P Tian, Z An, F Zhou - The Journal of Supercomputing, 2025 - Springer
Inductive link prediction (ILP) in knowledge graphs (KG) is gaining significant attention,
focusing on predicting missing triples involving unseen entities during training. While …

Multimodal Graph-based Variational Mixture of Experts Network for Zero-shot Multimodal Information Extraction

B Zhou, Y Zhang, Y Zhao, X Sui, X Yuan - THE WEB CONFERENCE 2025 - openreview.net
Multimodal information extraction on social media is a series of fundamental tasks to
construct the multimodal knowledge graph. The tasks are defined to extract the structural …