Attribute-Consistent Knowledge Graph Representation Learning for Multi-Modal Entity Alignment

TL;DR

This paper introduces ACK-MMEA, a novel framework for multi-modal entity alignment that addresses attribute gaps by creating attribute-consistent knowledge graphs and using relation-aware graph neural networks, leading to improved alignment accuracy.

Contribution

The paper proposes a new attribute-consistent knowledge graph construction method and a relation-aware GNN model for better multi-modal entity alignment, addressing contextual gap issues.

Findings

Achieves superior performance on benchmark datasets

Effectively compensates for attribute contextual gaps

Demonstrates robustness with relation-aware GNNs

Abstract

The multi-modal entity alignment (MMEA) aims to find all equivalent entity pairs between multi-modal knowledge graphs (MMKGs). Rich attributes and neighboring entities are valuable for the alignment task, but existing works ignore contextual gap problems that the aligned entities have different numbers of attributes on specific modality when learning entity representations. In this paper, we propose a novel attribute-consistent knowledge graph representation learning framework for MMEA (ACK-MMEA) to compensate the contextual gaps through incorporating consistent alignment knowledge. Attribute-consistent KGs (ACKGs) are first constructed via multi-modal attribute uniformization with merge and generate operators so that each entity has one and only one uniform feature in each modality. The ACKGs are then fed into a relation-aware graph neural network with random dropouts, to obtain aggregated relation representations and robust entity representations. In order to evaluate the ACK-MMEA facilitated for entity alignment, we specially design a joint alignment loss for both entity and attribute evaluation. Extensive experiments conducted on two benchmark datasets show that our approach achieves excellent performance compared to its competitors.