mlsanityData to 7 Oct 2026

Deep Active Alignment of Knowledge Graph Entities and Schemata

arXiv 2304.04389 ↗First posted 10 Apr 2023cs.DB cs.AIcited by 6

Not on the map. Why?

Abstract (arXiv)

Knowledge graphs (KGs) store rich facts about the real world. In this paper, we study KG alignment, which aims to find alignment between not only entities but also relations and classes in different KGs. Alignment at the entity level can cross-fertilize alignment at the schema level. We propose a new KG alignment approach, called DAAKG, based on deep learning and active learning. With deep learning, it learns the embeddings of entities, relations and classes, and jointly aligns them in a semi-supervised manner. With active learning, it estimates how likely an entity, relation or class pair can be inferred, and selects the best batch for human labeling. We design two approximation algorithms for efficient solution to batch selection. Our experiments on benchmark datasets show the superior accuracy and generalization of DAAKG and validate the effectiveness of all its modules.

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Builds on 38 of its 73 references that are in the map. First posted on arXiv 10 Apr 2023.

Builds on

38 of 73 references.

References · 38

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2017On Calibration of Modern Neural Networkscited by 4,860
  3. 2019RotatE: Knowledge Graph Embedding by Relational Rotation in Complex Spacecited by 893
  4. 2017Focal Loss for Dense Object Detectioncited by 749
  5. 2020A Survey on Knowledge Graphs: Representation, Acquisition and Applicationscited by 643
  6. 2019Deep Batch Active Learning by Diverse, Uncertain Gradient Lower Boundscited by 602
  7. 2020A Survey of Deep Active Learningcited by 547
  8. 2019Composition-based Multi-Relational Graph Convolutional Networkscited by 395
  9. 2020Low-Dimensional Hyperbolic Knowledge Graph Embeddingscited by 195
  10. 2020Deep Entity Matching with Pre-Trained Language Modelscited by 143
  11. 2016Multilingual Knowledge Graph Embeddings for Cross-lingual Knowledge Alignmentcited by 128
  12. 2017Cross-lingual Entity Alignment via Joint Attribute-Preserving Embeddingcited by 126
26 more
  1. 2019Multi-relational Poincar'e Graph Embeddingscited by 126
  2. 2020A Benchmarking Study of Embedding-based Entity Alignment for Knowledge Graphscited by 119
  3. 2019Knowledge Graph Alignment Network with Gated Multi-hop Neighborhood Aggregationcited by 101
  4. 2014Lazier Than Lazy Greedycited by 97
  5. 2019Multi-Channel Graph Neural Network for Entity Alignmentcited by 86
  6. 2019Learning to Exploit Long-term Relational Dependencies in Knowledge Graphscited by 83
  7. 2019Multi-view Knowledge Graph Embedding for Entity Alignmentcited by 74
  8. 2017DeepER -- Deep Entity Resolutioncited by 54
  9. 2020Visual Pivoting for (Unsupervised) Entity Alignmentcited by 46
  10. 2021BERTMap: A BERT-based Ontology Alignment Systemcited by 45
  11. 2019Low-resource Deep Entity Resolution with Transfer and Active Learningcited by 37
  12. 2020Realistic Re-evaluation of Knowledge Graph Completion Methods: An Experimental Studycited by 37
  13. 2021Universal Representation Learning of Knowledge Bases by Jointly Embedding Instances and Ontological Conceptscited by 37
  14. 2021Boosting the Speed of Entity Alignment 10*: Dual Attention Matching Network with Normalized Hard Sample Miningcited by 37
  15. 2021A Benchmark and Comprehensive Survey on Knowledge Graph Entity Alignment via Representation Learningcited by 31
  16. 2019Collective Entity Alignment via Adaptive Featurescited by 30
  17. 2020DyERNIE: Dynamic Evolution of Riemannian Manifold Embeddings for Temporal Knowledge Graph Completioncited by 30
  18. 2021LargeEA: Aligning Entities for Large-scale Knowledge Graphscited by 26
  19. 2021Knowing the No-match: Entity Alignment with Dangling Casescited by 20
  20. 2022ClusterEA: Scalable Entity Alignment with Stochastic Training and Normalized Mini-batch Similaritiescited by 20
  21. 2021ActiveEA: Active Learning for Neural Entity Alignmentcited by 11
  22. 2021Deep Indexed Active Learning for Matching Heterogeneous Entity Representationscited by 9
  23. 2020CorDEL: A Contrastive Deep Learning Approach for Entity Linkagecited by 7
  24. 2020Active Deep Learning on Entity Resolution by Risk Samplingcited by 6
  25. 2022Dangling-Aware Entity Alignment with Mixed High-Order Proximitiescited by 4
  26. 2020Crowdsourced Collective Entity Resolution with Relational Match Propagationcited by 1

Built on by

Cited by year

Citing papers per year: 2023: 1; 2024: 1; 2025: 4.

6 papers.

  1. 2023Rethinking Uncertainly Missing and Ambiguous Visual Modality in Multi-Modal Entity Alignmentcited by 20
  2. 2024LLM+KG@VLDB'24 Workshop Summarycited by 3
  3. 2025Tabular Embeddings for Tables with Bi-Dimensional Hierarchical Metadata and Nestingcited by 1
  4. 2025OntoAligner Meets Knowledge Graph Embedding Alignerscited by 1
  5. 2025Full Triple Matcher: Integrating all triple elements between heterogeneous Knowledge Graphscited by 0
  6. 2025Interactive Query Answering on Knowledge Graphs with Soft Entity Constraintscited by 0