Abstract
Multi-modal Entity Alignment (MMEA) aims to find equivalent entities across different multi-modal knowledge graphs (MMKGs). Most existing methods focus on how to encode or fuse information from different modalities effectively, without considering the critical interactions between entities, especially those between an entity and its neighbors within each modality. To fill the gap, we propose a novel model namely Enhanced Entity Interaction Modeling for Multi-modal Entity Alignment (EIEA). Specifically, we first utilize multiple separate pre-trained models to acquire single-modal data based entities’ embeddings. Then, the module Enhanced Entity Representation (EER) is designed to mine interactions between entities and their neighborhoods, and facilitate effective multi-modal embedding fusion using a weighting mechanism. Finally, through contrastive learning, we ensure that the aligned entities have higher similarity than non-aligned ones within each modality. The extensive experiments demonstrate that EIEA outperforms the state-of-the-art baselines on three benchmark datasets.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Bertasius, G., Wang, H., et al.: Is space-time attention all you need for video understanding? In: ICML, pp. 813–824 (2021)
Chen, L., Li, Z., et al.: MMEA: entity alignment for multi-modal knowledge graph. In: KSEM, pp. 134–147 (2020)
Chen, L., Li, Z., et al.: Multi-modal Siamese Network for Entity Alignment. In: KDD, pp. 118–126 (2022)
Chen, M., Tian, Y., et al.: Multilingual knowledge graph embeddings for cross-lingual knowledge alignment. In: IJCAI, pp. 1511–1517 (2017)
Guo, H., Tang, J., et al.: Multi-modal entity alignment in hyperbolic space. Neurocomputing 461, 598–607 (2021)
Hua, W., Dai, Z., et al.: Transformer quality in linear time. In: ICML, pp. 9099–9117 (2022)
Huang, G., Liu, Z., et al.: Densely connected convolutional networks. In: CVPR, pp. 2261–2269 (2017)
Li, C., Cao, Y., et al.: Semi-supervised entity alignment via joint knowledge embedding model and cross-graph model. In: EMNLP-IJCNLP, pp. 2723–2732 (2019)
Lin, Z., Zhang, Z., et al.: Multi-modal contrastive representation learning for entity alignment. In: COLING, pp. 2572–2584 (2022)
Liu, F., Chen, M., et al.: Visual pivoting for (unsupervised) entity alignment. In: AAAI, pp. 4257–4266 (2021)
Liu, Y., Li, H., Garcia-Duran, A., Niepert, M., Onoro-Rubio, D., Rosenblum, D.S.: MMKG: multi-modal knowledge graphs. In: Hitzler, P., et al. (eds.) ESWC 2019. LNCS, vol. 11503, pp. 459–474. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-21348-0_30
Liu, Z., Cao, Y., et al.: Exploring and evaluating attributes, values, and structures for entity alignment. In: EMNLP, pp. 6355–6364 (2020)
Pei, S., Yu, L., et al.: Semi-supervised entity alignment via knowledge graph embedding with awareness of degree difference. In: WWW, pp. 3130–3136 (2019)
Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. In: ICLR (2015)
Sun, Z., Chen, M., et al.: Knowledge association with hyperbolic knowledge graph embeddings. In: EMNLP, pp. 5704–5716 (2020)
Sun, Z., Hu, W., et al.: Bootstrapping entity alignment with knowledge graph embedding. In: IJCAI, pp. 4396–4402 (2018)
Velickovic, P., Cucurull, G., et al.: Graph attention networks. In: ICLR (2018)
Wang, S., Li, B.Z., et al.: Linformer: self-attention with linear complexity. CoRR abs/2006.04768 (2020)
Wang, Z., Lv, Q., et al.: Cross-lingual knowledge graph alignment via graph convolutional networks. In: EMNLP, pp. 349–357 (2018)
Wu, Z., Jain, P., et al.: Representing long-range context for graph neural networks with global attention. In: NeurIPS, pp. 13266–13279 (2021)
Yang, H., Zou, Y., et al.: Aligning cross-lingual entities with multi-aspect information. In: EMNLP-IJCNLP, pp. 4430–4440 (2019)
Zeng, W., Zhao, X., et al.: Reinforced active entity alignment. In: CIKM, pp. 2477–2486 (2021)
Zhang, R., Trisedya, B.D., et al.: A benchmark and comprehensive survey on knowledge graph entity alignment via representation learning. VLDB J. 31(5), 1143–1168 (2022)
Zhu, R., Ma, M., et al.: RAGA: relation-aware graph attention networks for global entity alignment. In: PAKDD, pp. 501–513 (2021)
Acknowledgments.
This work is supported by the National Natural Science Foundation of China No. 62272332, the Major Program of the Natural Science Foundation of Jiangsu Higher Education Institutions of China No. 22KJA520006.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Li, J., Zhou, Q., Chen, W., Zhao, L. (2023). Enhanced Entity Interaction Modeling for Multi-Modal Entity Alignment. In: Jin, Z., Jiang, Y., Buchmann, R.A., Bi, Y., Ghiran, AM., Ma, W. (eds) Knowledge Science, Engineering and Management. KSEM 2023. Lecture Notes in Computer Science(), vol 14118. Springer, Cham. https://doi.org/10.1007/978-3-031-40286-9_18
Download citation
DOI: https://doi.org/10.1007/978-3-031-40286-9_18
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-40285-2
Online ISBN: 978-3-031-40286-9
eBook Packages: Computer ScienceComputer Science (R0)