Multi-Channel Graph Neural Network for Entity Alignment

By Yixin Cao, Zhiyuan Liu, Chengjiang Li, Zhiyuan Liu, Juan-Zi Li, Tat-seng Chua. Annual Meeting of the Association for Computational Linguistics, 2019

302 citations recorded by the source corpus.

Entity alignment typically suffers from the issues of structural heterogeneity and limited seed alignments. In this paper, we propose a novel Multi-channel Graph Neural Network model (MuGNN) to learn alignment-oriented knowledge graph (KG) embeddings by robustly encoding two KGs via multiple channels. Each channel encodes KGs via different relation weighting schemes with respect to self-attention towards KG completion and cross-KG attention for pruning exclusive entities respectively, which are further combined via pooling techniques. Moreover, we also infer and transfer rule knowledge for completing two KGs consistently. MuGNN is expected to reconcile the structural differences of two KGs, and thus make better use of seed alignments. Extensive experiments on five publicly available datasets demonstrate our superior performance (5% Hits@1 up on average). Source code and data used in the experiments can be accessed at https://github.com/thunlp/MuGNN .

Subfields: Artificial Intelligence, Management Science and Operations Research

View Paper: https://www.semanticscholar.org/paper/cf0f3b886f4d4ab232a2fdf47819c2a89a5b1625

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. Wei Hu
2. Zequn Sun
3. Muhao Chen
4. Chengming Wang
5. Yuzhong Qu
6. Wei Zhang
7. Jian Dai
8. Xindong Wu

In Management Science and Operations Research

1. Wei Hu
2. Zequn Sun
3. Xindong Wu
4. Hao Peng
5. Yuzhong Qu
6. Lingfeng Zhong
7. Muhao Chen
8. Qian Li

Citations in the corpus

• A benchmarking study of embedding-based entity alignment for knowledge graphs (2020, unknown): “MuGNN [8] Neighbor - Manhattan Calibration Superv.”
• Knowledge Graph Alignment Network with Gated Multi-hop Neighborhood Aggregation (2019, methodology): “2019), RSN (Guo, Sun, and Hu 2019) and MuGNN (Cao et al. 2019).”
• A Comprehensive Survey on Automatic Knowledge Graph Construction (2023, background): “MuGNN [320], for example, proposes a cross-knowledge graph attention mechanism with a multi-channel GNN encoder that can model inter-graph structural features consistently.”