Iterative Entity Alignment via Joint Knowledge Embeddings

By Hao Zhu, Ruobing Xie, Zhiyuan Liu, Maosong Sun. International Joint Conference on Artificial Intelligence, 2017

394 citations recorded by the source corpus.

Entity alignment aims to link entities and their counterparts among multiple knowledge graphs (KGs). Most existing methods typically rely on external information of entities such as Wikipedia links and require costly manual feature construction to complete alignment. In this paper, we present a novel approach for entity alignment via joint knowledge embeddings. Our method jointly encodes both entities and relations of various KGs into a unified low-dimensional semantic space according to a small seed set of aligned entities. During this process, we can align entities according to their semantic distance in this joint semantic space. More specifically, we present an iterative and parameter sharing method to improve alignment performance. Experiment results on realworld datasets show that, as compared to baselines, our method achieves significant improvements on entity alignment, and can further improve knowledge graph completion performance on various KGs with the favor of joint knowledge embeddings.

Subfields: Artificial Intelligence, Management Science and Operations Research

View Paper: https://www.semanticscholar.org/paper/76f9f4bf8d97de5e95d2fd9dd8b50041524fb1cc

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Philip S. Yu
2. Shirui Pan
3. Tat-seng Chua
4. Erik Cambria
5. Jimmy J. Lin
6. Peng Shi
7. Yixin Cao
8. Zhiyuan Liu

In Management Science and Operations Research

1. Tat-seng Chua
2. Yuzhong Qu
3. Yixin Cao
4. Wei Zhang
5. Zhichun Wang
6. Qingsong Lv
7. Yu Zhang
8. Xiaohan Lan

Citations in the corpus

• Entity Alignment between Knowledge Graphs Using Attribute Embeddings (2019, methodology): “To address this problem, Chen et al. (2017a; 2017b) and Zhu et al. (2017) learn an embedding space for each KG separately and propose to use a transition matrix to map the embedding space from one KG to the other.”
• A Survey on Knowledge Graphs: Representation, Acquisition, and Applications (2020, background): “Following the translation-based and linear transformation models, IPTransE [126] proposes an iterative alignment model by mapping entities into a unified representation space under a joint embedding framework (Fig.”
• Knowledge Graph Alignment Network with Gated Multi-hop Neighborhood Aggregation (2019, methodology): “We compare with recent embedding-based entity alignment models: MTransE (Chen et al. 2017), IPTransE (Zhu et al. 2017), JAPE (Sun, Hu, and Li 2017), AlignE (Sun et al. 2018), GCN-Align (Wang et al. 2018), SEA (Pei et al. 2019), RSN (Guo, Sun, and Hu 2019) and MuGNN (Cao et al. 2019).”
• Multi-Channel Graph Neural Network for Entity Alignment (2019, methodology): “Instead, recent work utilizes general KG embedding methods (e.g., TransE (Bor-des et al., 2013)) and align equivalent entities into a unified vector space based on a few seed alignments (Chen et al., 2017; Sun et al., 2017; Zhu et al., 2017; Chen et al., 2018; Sun et al., 2018; Wang et al., 2018b).”
• Aligning Cross-Lingual Entities with Multi-Aspect Information (2019, background): “Recently, embedding-based solutions (Chen et al., 2017b; Sun et al., 2017; Zhu et al., 2017; Wang et al., 2018; Chen et al., 2018) have been proposed to unify multilingual KGs into the same low-dimensional vector space where equivalent entities are close to each other.”
• Bootstrapping Entity Alignment with Knowledge Graph Embedding (2018, methodology): “IPTransE [ Zhu et al. , 2017 ] employs PTransE [ Lin et al. , 2015a ] to embed a single KG and integrates three modules (translation-based, linear transformation and parameter sharing) for jointly embedding different KGs.”
• Learning to Exploit Long-term Relational Dependencies in Knowledge Graphs (2019, methodology): “For entity alignment, we picked up several state-of-the-art embedding-based methods for comparison: MTransE (Chen et al., 2017), IPTransE (Zhu et al., 2017), JAPE (Sun et al., 2017), BootEA (Sun et al., 2018) and GCN-Align (Wang et al., 2018).”
• A benchmarking study of embedding-based entity alignment for knowledge graphs (2020, critical): “The over(cid:12)tting issue in MTransE, the bootstrapping errors in IPTransE and the fuzzy entity clusters in JAPE are the reasons for their non-discriminative embeddings.”
• Cross-lingual Knowledge Graph Alignment via Graph Convolutional Networks (2018, methodology): “For example, JE, MTransE, and ITransE all use hyper-parameters to weight the loss of entity alignments in the loss functions of their models; JAPE uses the pre-aligned entities to combine two KGs as one, and adds weight to the scores of negative samples in its loss function.”