Jointly Learning Knowledge Embedding and Neighborhood Consensus with Relational Knowledge Distillation for Entity Alignment
On the map: Knowledge distillation → Graph neural network distillation
Abstract (arXiv)
Entity alignment aims at integrating heterogeneous knowledge from different knowledge graphs. Recent studies employ embedding-based methods by first learning the representation of Knowledge Graphs and then performing entity alignment via measuring the similarity between entity embeddings. However, they failed to make good use of the relation semantic information due to the trade-off problem caused by the different objectives of learning knowledge embedding and neighborhood consensus. To address this problem, we propose Relational Knowledge Distillation for Entity Alignment (RKDEA), a Graph Convolutional Network (GCN) based model equipped with knowledge distillation for entity alignment. We adopt GCN-based models to learn the representation of entities by considering the graph structure and incorporating the relation semantic information into GCN via knowledge distillation. Then, we introduce a novel adaptive mechanism to transfer relational knowledge so as to jointly learn entity embedding and neighborhood consensus. Experimental results on several benchmarking datasets demonstrate the effectiveness of our proposed model.
Key facts. Cited by 2 papers in the map (data through 13 Oct 2026). Placed in Graph neural network distillation, one of 12 directions in Knowledge distillation. Builds on 24 of its 62 references that are in the map. First posted on arXiv 25 Jan 2022.
Builds on
24 of 62 references.
References · 24
- 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,318
- 2015Distilling the Knowledge in a Neural Networkcited by 10,180
- 2017Modeling Relational Data with Graph Convolutional Networkscited by 1,689
- 2014FitNets: Hints for Thin Deep Netscited by 1,631
- 2016Paying More Attention to Attention: Improving the Performance of Convolutional Neural Networks via Attention Transfercited by 1,067
- 2019Relational Knowledge Distillationcited by 881
- 2018Born Again Neural Networkscited by 541
- 2015Highway Networkscited by 259
- 2018Neighbourhood Consensus Networkscited by 173
- 2016Multilingual Knowledge Graph Embeddings for Cross-lingual Knowledge Alignmentcited by 128
- 2017Cross-lingual Entity Alignment via Joint Attribute-Preserving Embeddingcited by 126
- 2019Relation-Aware Entity Alignment for Heterogeneous Knowledge Graphscited by 106
12 more
- 2019Knowledge Graph Alignment Network with Gated Multi-hop Neighborhood Aggregationcited by 101
- 2019Multi-Channel Graph Neural Network for Entity Alignmentcited by 86
- 2019Learning to Exploit Long-term Relational Dependencies in Knowledge Graphscited by 83
- 2019Multi-view Knowledge Graph Embedding for Entity Alignmentcited by 74
- 2019Cross-lingual Knowledge Graph Alignment via Graph Matching Neural Networkcited by 68
- 2018Label Refinery: Improving ImageNet Classification through Label Progressioncited by 65
- 2020Exploring and Evaluating Attributes, Values, and Structures for Entity Alignmentcited by 63
- 2017DarkRank: Accelerating Deep Metric Learning via Cross Sample Similarities Transfercited by 56
- 2020Neighborhood Matching Network for Entity Alignmentcited by 44
- 2019Jointly Learning Entity and Relation Representations for Entity Alignmentcited by 39
- 2019JarKA: Modeling Attribute Interactions for Cross-lingual Knowledge Alignmentcited by 19
- 2016Intrinsic Geometric Information Transfer Learning on Multiple Graph-Structured Datasetscited by 18
Built on by
Citing papers per year: 2023: 1; 2024: 0; 2025: 1.
2 papers.