BERT-INT: A BERT-based Interaction Model For Knowledge Graph Alignment

By Kwei-Herng Lai, Daochen Zha, Yuening Li, Xia Hu. 2020

197 citations recorded by the source corpus.

Knowledge graph alignment aims to link equivalent entities across different knowledge graphs. To utilize both the graph structures and the side information such as name, description and attributes, most of the works propagate the side information especially names through linked entities by graph neural networks. However, due to the heterogeneity of different knowledge graphs, the alignment accuracy will be suffered from aggregating different neighbors. This work presents an interaction model to only leverage the side information. Instead of aggregating neighbors, we compute the interactions between neighbors which can capture fine-grained matches of neighbors. Similarly, the interactions of attributes are also modeled. Experimental results show that our model significantly outperforms the best state-of-the-art methods by 1.9-9.7% in terms of HitRatio@1 on the dataset DBP15K.

Subfields: Artificial Intelligence, Management Science and Operations Research

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. Dacheng Tao
2. Jianping Gou
3. S. Maybank
4. Baosheng Yu
5. Xia Hu
6. Kaixiong Zhou
7. Daochen Zha
8. Kwei-Herng Lai

In Management Science and Operations Research

1. Dacheng Tao
2. Xia Hu
3. Kaixiong Zhou

Citations in the corpus

• Knowledge Distillation: A Survey (2020, background): “, 2012), reinforcement learning (Silver et al., 2016; Ashok et al., 2018; Lai et al., 2020), and natural language processing (Devlin et al.”
• Simplifying Deep Reinforcement Learning via Self-Supervision (2021, background): “Dual Policy Distillation (Lai et al. 2020) instantiates a peer agent and performs imitation learning with each other to improve sample efficiency.”