Knowledge graph embedding methods for entity alignment: experimental review

N Fanourakis, V Efthymiou, D Kotzinos… - Data Mining and …, 2023 - Springer
In recent years, we have witnessed the proliferation of knowledge graphs (KG) in various
domains, aiming to support applications like question answering, recommendations, etc. A …

Selfkg: Self-supervised entity alignment in knowledge graphs

X Liu, H Hong, X Wang, Z Chen, E Kharlamov… - Proceedings of the …, 2022 - dl.acm.org
Entity alignment, aiming to identify equivalent entities across different knowledge graphs
(KGs), is a fundamental problem for constructing Web-scale KGs. Over the course of its …

Multi-modal contrastive representation learning for entity alignment

Z Lin, Z Zhang, M Wang, Y Shi, X Wu… - arxiv preprint arxiv …, 2022 - arxiv.org
Multi-modal entity alignment aims to identify equivalent entities between two different multi-
modal knowledge graphs, which consist of structural triples and images associated with …

Meaformer: Multi-modal entity alignment transformer for meta modality hybrid

Z Chen, J Chen, W Zhang, L Guo, Y Fang… - Proceedings of the 31st …, 2023 - dl.acm.org
Multi-modal entity alignment (MMEA) aims to discover identical entities across different
knowledge graphs (KGs) whose entities are associated with relevant images. However …

Clusterea: Scalable entity alignment with stochastic training and normalized mini-batch similarities

Y Gao, X Liu, J Wu, T Li, P Wang, L Chen - Proceedings of the 28th ACM …, 2022 - dl.acm.org
Entity alignment (EA) aims at finding equivalent entities in different knowledge graphs (KGs).
Embedding-based approaches have dominated the EA task in recent years. Those methods …

A critical re-evaluation of neural methods for entity alignment

M Leone, S Huber, A Arora, A García-Durán… - Proceedings of the …, 2022 - dl.acm.org
Neural methods have become the de-facto choice for the vast majority of data analysis tasks,
and entity alignment (EA) is no exception. Not surprisingly, more than 50 different neural EA …

Revisiting embedding-based entity alignment: A robust and adaptive method

Z Sun, W Hu, C Wang, Y Wang… - IEEE Transactions on …, 2022 - ieeexplore.ieee.org
Entity alignment—the discovery of identical entities across different knowledge graphs (KGs)—
is a critical task in data fusion. In this paper, we revisit existing entity alignment methods in …

Rethinking uncertainly missing and ambiguous visual modality in multi-modal entity alignment

Z Chen, L Guo, Y Fang, Y Zhang, J Chen… - International Semantic …, 2023 - Springer
As a crucial extension of entity alignment (EA), multi-modal entity alignment (MMEA) aims to
identify identical entities across disparate knowledge graphs (KGs) by exploiting associated …

Hierarchical feature aggregation based on transformer for image-text matching

X Dong, H Zhang, L Zhu, L Nie… - IEEE Transactions on …, 2022 - ieeexplore.ieee.org
In order to carry out more accurate retrieval across image-text modalities, some scholars use
fine-grained feature to align image and text. Most of them directly use attention mechanism …

Largeea: Aligning entities for large-scale knowledge graphs

C Ge, X Liu, L Chen, B Zheng, Y Gao - arxiv preprint arxiv:2108.05211, 2021 - arxiv.org
Entity alignment (EA) aims to find equivalent entities in different knowledge graphs (KGs).
Current EA approaches suffer from scalability issues, limiting their usage in real-world EA …