Research map / Graph learning / Knowledge and temporal graphs
Entity Alignment between Knowledge Graphs Using Attribute Embeddings
Bayu Distiawan Trisedya, Jianzhong Qi, Rui Zhang
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| attribute character embeddings to unify KG embedding spaces | embedding-based entity alignment · DBP-LGD | Hits@1: 33.33 -> 85.32 | Improved |
| attribute character embeddings to unify KG embedding spaces | embedding-based entity alignment · DBP-YAGO | Hits@1: 33.46 -> 91.02 | Improved |
| add transitivity rule to enrich entity attributes (ablation) | N-gram attribute embedding model · DBP-LGD | Hits@1: 84.27 -> 85.32 | Improved |
| add transitivity rule to enrich entity attributes (ablation) | N-gram attribute embedding model · DBP-YAGO | Hits@1: 89.69 -> 91.02 | Improved |
| N-gram compositional function instead of LSTM (ablation) | attribute character embedding · DBP-LGD | Hits@1: 60.72 -> 84.27 | Improved |
| N-gram compositional function instead of SUM (ablation) | attribute character embedding · DBP-GEO | Hits@1: 51.33 -> 87.61 | Improved |
| add learned embeddings as feature to label string rule | rule-based alignment · DBP-LGD | Hits@1: 80.52 -> 88.91 | Improved |
| alignment-oriented training (alpha) vs TransE | KG completion · LGD link prediction | Hits@10: 78.80 -> 75.69 | No clear effect |
Closest papers by meaning
- What Makes Entities Similar? A Similarity Flooding Perspective for Multi-sourced Knowledge Graph Embeddings (ICML 2023 · similarity 0.93)
- COTSAE: CO-Training of Structure and Attribute Embeddings for Entity Alignment (AAAI 2020 · similarity 0.92)
- Clustering then Propagation: Select Better Anchors for Knowledge Graph Embedding (NeurIPS 2024 · similarity 0.88)
- Select and Augment: Enhanced Dense Retrieval Knowledge Graph Augmentation (Abstract Reprint) (AAAI 2024 · similarity 0.88)
- HLMEA: Unsupervised Entity Alignment Based on Hybrid Language Models (AAAI 2025 · similarity 0.88)
- Knowledge Graph Completion with Relation-Aware Anchor Enhancement (AAAI 2025 · similarity 0.88)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
