Saved in:
Bibliographic Details
Main Authors: Hu, Zhiwei, Gutiérrez-Basulto, Víctor, Xiang, Zhiliang, Li, Ru, Pan, Jeff Z.
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2404.17590
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909183622774784
author Hu, Zhiwei
Gutiérrez-Basulto, Víctor
Xiang, Zhiliang
Li, Ru
Pan, Jeff Z.
author_facet Hu, Zhiwei
Gutiérrez-Basulto, Víctor
Xiang, Zhiliang
Li, Ru
Pan, Jeff Z.
contents Multi-modal entity alignment (MMEA) aims to identify equivalent entity pairs across different multi-modal knowledge graphs (MMKGs). Existing approaches focus on how to better encode and aggregate information from different modalities. However, it is not trivial to leverage multi-modal knowledge in entity alignment due to the modal heterogeneity. In this paper, we propose a Multi-Grained Interaction framework for Multi-Modal Entity Alignment (MIMEA), which effectively realizes multi-granular interaction within the same modality or between different modalities. MIMEA is composed of four modules: i) a Multi-modal Knowledge Embedding module, which extracts modality-specific representations with multiple individual encoders; ii) a Probability-guided Modal Fusion module, which employs a probability guided approach to integrate uni-modal representations into joint-modal embeddings, while considering the interaction between uni-modal representations; iii) an Optimal Transport Modal Alignment module, which introduces an optimal transport mechanism to encourage the interaction between uni-modal and joint-modal embeddings; iv) a Modal-adaptive Contrastive Learning module, which distinguishes the embeddings of equivalent entities from those of non-equivalent ones, for each modality. Extensive experiments conducted on two real-world datasets demonstrate the strong performance of MIMEA compared to the SoTA. Datasets and code have been submitted as supplementary materials.
format Preprint
id arxiv_https___arxiv_org_abs_2404_17590
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Leveraging Intra-modal and Inter-modal Interaction for Multi-Modal Entity Alignment
Hu, Zhiwei
Gutiérrez-Basulto, Víctor
Xiang, Zhiliang
Li, Ru
Pan, Jeff Z.
Information Retrieval
Artificial Intelligence
Multi-modal entity alignment (MMEA) aims to identify equivalent entity pairs across different multi-modal knowledge graphs (MMKGs). Existing approaches focus on how to better encode and aggregate information from different modalities. However, it is not trivial to leverage multi-modal knowledge in entity alignment due to the modal heterogeneity. In this paper, we propose a Multi-Grained Interaction framework for Multi-Modal Entity Alignment (MIMEA), which effectively realizes multi-granular interaction within the same modality or between different modalities. MIMEA is composed of four modules: i) a Multi-modal Knowledge Embedding module, which extracts modality-specific representations with multiple individual encoders; ii) a Probability-guided Modal Fusion module, which employs a probability guided approach to integrate uni-modal representations into joint-modal embeddings, while considering the interaction between uni-modal representations; iii) an Optimal Transport Modal Alignment module, which introduces an optimal transport mechanism to encourage the interaction between uni-modal and joint-modal embeddings; iv) a Modal-adaptive Contrastive Learning module, which distinguishes the embeddings of equivalent entities from those of non-equivalent ones, for each modality. Extensive experiments conducted on two real-world datasets demonstrate the strong performance of MIMEA compared to the SoTA. Datasets and code have been submitted as supplementary materials.
title Leveraging Intra-modal and Inter-modal Interaction for Multi-Modal Entity Alignment
topic Information Retrieval
Artificial Intelligence
url https://arxiv.org/abs/2404.17590