| Year | Title | Venue | Paper | Code |
|---|---|---|---|---|
| 2020 | A benchmarking study of embedding-based entity alignment for knowledge graphs | VLDB | ||
| 2021 | A comprehensive survey of entity alignment for knowledge graphs | AI Open | ||
| 2022 | An Experimental Study of State-of-the-Art Entity Alignment Approaches | TKDE |
| Year | Abbr. | Title | Venue | Paper | Code |
|---|---|---|---|---|---|
| 2017 | MTransE | Multilingual Knowledge Graph Embeddings for Cross-lingual Knowledge Alignment | IJCAI | ||
| 2017 | IPTransE | Iterative Entity Alignment via Knowledge Embeddings | IJCAI | ||
| 2017 | JAPE | Cross-lingual entity alignment via joint attribute-preserving embedding | ISWC | ||
| 2018 | BootEA | Bootstrapping Entity Alignment with Knowledge Graph Embedding | IJCAI | ||
| 2018 | GCN-Align | Cross-lingual Knowledge Graph Alignment via Graph Convolutional Networks | EMNLP | ||
| 2019 | RSNs | Learning to Exploit Long-term Relational Dependencies in Knowledge Graphs | ICML | ||
| 2019 | Two-stage entity alignment: Combining hybrid knowledge graph embedding with similarity-based relation alignment | PRICAI | |||
| 2019 | AliNet | Knowledge Graph Alignment Network with Gated Multi-Hop Neighborhood Aggregation | AAAI | ||
| 2019 | Entity Alignment between Knowledge Graphs Using Attribute | AAAI | |||
| 2019 | SEA | Semi-Supervised Entity Alignment via Knowledge Graph Embedding with Awareness of Degree Difference | |||
| 2019 | GMNN | Cross-lingual Knowledge Graph Alignment via Graph Matching Neural Network | ACL | ||
| 2019 | MuGNN | Multi-Channel Graph Neural Network for Entity Alignment | ACL | ||
| 2019 | RDGCN | Relation-Aware Entity Alignment for Heterogeneous Knowledge Graphs | ACL | ||
| 2019 | TransEdge | TransEdge: Translating Relation-Contextualized Embeddings for Knowledge Graphs | ISWC | ||
| 2019 | HMAN | Aligning Cross-Lingual Entities with Multi-Aspect Information | EMNLP | ||
| 2019 | Semi-supervised Entity Alignment via Joint Knowledge Embedding Model and Cross-graph Model | EMNLP | |||
| 2019 | HGCN | Jointly Learning Entity and Relation Representations for Entity Alignment | EMNLP | ||
| 2019 | MultiKE | Multi-view Knowledge Graph Embedding for Entity Alignment | IJCAI | ||
| 2019 | NAEA | Neighborhood-Aware Attentional Representation for Multilingual Knowledge Graphs | IJCAI | ||
| 2020 | DAT | Degree-Aware Alignment for Entities in Tail | SIGIR | ||
| 2020 | NMN | Neighborhood Matching Network for Entity Alignment | ACL | ||
| 2020 | REA | Robust Cross-lingual Entity Alignment between Knowledge Graphs | KDD | ||
| 2020 | HyperKE | Knowledge Association with Hyperbolic Knowledge Graph Embeddings | EMNLP | ||
| 2020 | AttrGNN | Exploring and Evaluating Attributes, Values, and Structures for Entity Alignment | EMNLP | ||
| 2020 | MRAEA | MRAEA: An efficient and robust entity alignment approach for cross-lingual knowledge graph | WSDM | ||
| 2020 | REA | Relational Reflection Entity Alignment | CIKM | ||
| 2020 | CEA | Collective entity alignment via adaptive features | ICDE | ||
| 2020 | JarKA | JarKA: Modeling Attribute Interactions for Cross-lingual Knowledge Alignment | PAKDD | [code] | |
| 2020 | Entity Alignment for Knowledge Graphs with Multi-order Convolutional Networks | TKDE | |||
| 2021 | Network Alignment with Holistic Embeddings | TKDE | |||
| 2021 | Towards Entity Alignment in the Open World: An Unsupervised Approach | DASFAA | |||
| 2021 | EVA | Visual Pivoting for (Unsupervised) Entity Alignment | AAAI | ||
| 2021 | Relation-Aware Neighborhood Matching Model for Entity Alignment | AAAI | |||
| 2021 | EASY | Make It Easy: An Effective End-to-End Entity Alignment Framework | SIGIR | ||
| 2021 | LargeEA | LargeEA: Aligning Entities for Large-scale Knowledge Graphs | VLDB | ||
| 2021 | RAC | Reinforced Active Entity Alignment | CIKM | ||
| 2021 | PSR | Are Negative Samples Necessary in Entity Alignment?: An Approach with High Performance, Scalability and Robustness | CIKM | ||
| 2021 | KE-GCN | Knowledge Embedding Based Graph Convolutional Network | WWW | ||
| 2021 | Boosting the speed of entity alignment 10X: dual attention matching network with normalized hard sample mining | WWW | |||
| 2022 | Temporal Knowledge Graph Entity Alignment via Representation Learning | DASFAA | |||
| 2022 | Ensemble Semi-supervised Entity Alignment via Cycle-teaching | AAAI | |||
| 2022 | Multilingual Knowledge Graph Completion with Self-Supervised Adaptive Graph Alignment | ACL | |||
| 2022 | An Effective and Efficient Entity Alignment Decoding Algorithm via Third-Order Tensor Isomorphism | ACL | |||
| 2022 | Understanding and Improving Knowledge Graph Embedding for Entity Alignment | ICML | |||
| 2022 | Dangling-Aware Entity Alignment with Mixed High-Order Proximities | NAACL | |||
| 2022 | IMEA | Informed multi-context entity alignment | WSDM | ||
| 2022 | Graph Alignment with Noisy Supervision | WWW | |||
| 2022 | Uncertainty-aware Pseudo Label Refinery for Entity Alignment | WWW | |||
| 2022 | SelfKG | SelfKG: Self-Supervised Entity Alignment in Knowledge Graphs | WWW | [Code] | |
| 2022 | ContEA | Facing Changes: Continual Entity Alignment for Growing Knowledge Graphs | ISWC | ||
| 2022 | Semantics Driven Embedding Learning for Effective Entity Alignment | ICDE | |||
| 2022 | Large-scale Entity Alignment via Knowledge Graph Merging, Partitioning and Embedding | CIKM | |||
| 2022 | Interactive Contrastive Learning for Self-Supervised Entity Alignment | CIKM | |||
| 2022 | Multi-modal Contrastive Representation Learning for Entity Alignment | COLING | |||
| 2022 | RoadEA | Revisiting Embedding-based Entity Alignment: A Robust and Adaptive Method | TKDE | ||
| 2022 | A multiscale convolutional gragh network using only structural information for entity alignment | Applied Intelligence |
| Dataset names | tasks | Languages | #Entities | Venue | Link |
| DBP15K | ZH-EN, JA-EN, FR-EN | Cross-lingual | 15K | ISWC2017 | [Link] |
| DWY100K | DBP-WD, DBP-YG | English | 100K | IJCAI2018 | [Link] |
| SRPRS | EN-FR, EN-DE | Cross-lingual | Normal/Dense | ICML2019 | [Link] |
| OpenEA (IDS) | EN-FR-15K, EN-DE-15K | Cross-lingual | 15K | VLDB2020 | [Link] |
| D-W-15K, D-Y-15K | English | 15K | |||
| EN-FR-100K, EN-DE-100K | Cross-lingual | 100K | |||
| D-W-100K, D-Y-100K | English | 100K | |||
| DBP1M | EN-FR, EN-DE | Cross-lingual | 1M | VLDB2021 | [Link] |
D means DBpedia, W means Wikidata, and Y means YOGO3.
SRPRS means segment-based random PageRank sampling, while IDS means Iterative degree-based sampling. Both of them indicates that several EA benchmarks (e.g., DBP15K and DWY100K) contain much more highdegree entities than real-world KGs do.
DBP1M was proposed by LargeEA, which mainly focus on the Large-scale Knowledge Graphs.
React
Typescript
Django
Laravel
Facebook
Microsoft
Google
Alibaba
D3
Tencent