Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
129 tokens/sec
GPT-4o
28 tokens/sec
Gemini 2.5 Pro Pro
42 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Deep Active Alignment of Knowledge Graph Entities and Schemata (2304.04389v3)

Published 10 Apr 2023 in cs.DB and cs.AI

Abstract: 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.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (71)
  1. Realistic Re-evaluation of Knowledge Graph Completion Methods: An Experimental Study. In SIGMOD. ACM, Portland, OR, USA, 1995–2010.
  2. Deep Batch Active Learning by Diverse, Uncertain Gradient Lower Bounds. In ICLR. OpenReview.net, Addis Ababa, Ethiopia. https://openreview.net/forum?id=ryghZJBKPS
  3. Multi-relational Poincaré Graph Embeddings. In NeurIPS. Curran Associates Inc., Vancouver, BC, Canada, 4465–4475.
  4. Translating Embeddings for Modeling Multi-relational Data. In NIPS. Curran Associates Inc., Lake Tahoe, NV, USA, 2787–2795.
  5. Ursin Brunner and Kurt Stockinger. 2020. Entity Matching with Transformer Architectures - A Step Forward in Data Integration. In EDBT. OpenProceedings.org, Copenhagen, Denmark, 463–473.
  6. Multi-Channel Graph Neural Network for Entity Alignment. In ACL. ACL, Florence, Italy, 1452–1461.
  7. A Partial-Order-Based Framework for Cost-Effective Crowdsourced Entity Resolution. The VLDB Journal 27, 6 (2018), 745–770.
  8. Low-Dimensional Hyperbolic Knowledge Graph Embeddings. In ACL. ACL, Online, 6901–6914.
  9. Augmenting Ontology Alignment by Semantic Embedding and Distant Supervision. In ESWC. Springer, Online, 392–408.
  10. Multi-modal Siamese Network for Entity Alignment. In KDD. ACM, Washington, D.C., USA, 118–126.
  11. Multilingual Knowledge Graph Embeddings for Cross-lingual Knowledge Alignment. In IJCAI. IJCAI, Melbourne, Australia, 1511–1517.
  12. Falcon: Scaling Up Hands-Off Crowdsourced Entity Matching to Build Cloud Services. In SIGMOD. ACM, Raleigh, NC, USA, 1431–1446.
  13. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. In NAACL-HLT. ACL, Minneapolis, MN, USA, 4171–4186.
  14. Distributed Representations of Tuples for Entity Resolution. Proceedings of the VLDB Endowment 11, 11 (2018), 1454–1467.
  15. Duplicate Record Detection: A Survey. IEEE Transactions on Knowledge and Data Engineering 19, 1 (2007), 1–16.
  16. Jérôme Euzenat and Pavel Shvaiko. 2013. Ontology Matching (second ed.). Springer-Verlag, Heidelberg.
  17. ClusterEA: Scalable Entity Alignment with Stochastic Training and Normalized Mini-batch Similarities. In KDD. ACM, Washington D.C., USA, 421–431.
  18. LargeEA: Aligning Entities for Large-scale Knowledge Graphs. Proceedings of the VLDB Endowment 15, 2 (2021), 237–245.
  19. Corleone: Hands-off Crowdsourcing for Entity Matching. In SIGMOD. ACM, Snowbird, UT, USA, 601–612.
  20. On Calibration of Modern Neural Networks. In ICML. PMLR, Sydney, Australia, 1321–1330.
  21. Learning to Exploit Long-term Relational Dependencies in Knowledge Graphs. In ICML. PMLR, Long Beach, CA, USA, 2505–2514.
  22. DyERNIE: Dynamic Evolution of Riemannian Manifold Embeddings for Temporal Knowledge Graph Completion. In EMNLP. ACL, Online, 7301–7316.
  23. Universal Representation Learning of Knowledge Bases by Jointly Embedding Instances and Ontological Concepts. In KDD. ACM, Anchorage, AK, USA, 1709–1719.
  24. Unsupervised Entity Alignment Using Attribute Triples and Relation Triples. In DASFAA. Springer, Chiang Mai, Thailand, 367–382.
  25. BERT-INT: A BERT-based Interaction Model For Knowledge Graph Alignment. In IJCAI. IJCAI, Online, 3174–3180.
  26. BERTMap: A BERT-Based Ontology Alignment System. In AAAI. AAAI Press, Online, 5684–5691.
  27. Deep Entity Matching with Adversarial Active Learning. The VLDB Journal 32, 1 (2023), 229–255.
  28. Crowdsourced Collective Entity Resolution with Relational Match Propagation. In ICDE. IEEE, Dallas, TX, USA, 37–48.
  29. Deep Indexed Active Learning for Matching Heterogeneous Entity Representations. Proceedings of the VLDB Endowment 15, 1 (2021), 31–45.
  30. A Survey on Knowledge Graphs: Representation, Acquisition, and Applications. IEEE Transactions on Neural Networks and Learning Systems 33, 2 (2021), 494–514.
  31. Low-resource Deep Entity Resolution with Transfer and Active Learning. In ACL. ACL, Florence, Italy, 5851–5861.
  32. DeepAlignment: Unsupervised Ontology Matching with Refined Word Vectors. In NAACL. ACL, New Orleans, LA, USA, 787–798.
  33. DBpedia - A Large-scale, Multilingual Knowledge Base Extracted from Wikipedia. Semantic Web 6, 2 (2015), 167–195.
  34. A Critical Re-evaluation of Neural Methods for Entity Alignment. Proceedings of the VLDB Endowment 15, 8 (2022), 1712–1725.
  35. Semi-supervised Entity Alignment via Joint Knowledge Embedding Model and Cross-graph Model. In EMNLP-IJCNLP. ACL, Hong Kong, China, 2723–2732.
  36. Deep Entity Matching with Pre-trained Language Models. Proceedings of the VLDB Endowment 14, 1 (2020), 50–60.
  37. Focal Loss for Dense Object Detection. IEEE Transactions on Pattern Analysis and Machine Intelligence 42, 2 (2020), 318–327.
  38. ActiveEA: Active Learning for Neural Entity Alignment. In EMNLP. ACL, Punta Cana, Dominican Republic, 3364–3374.
  39. Visual Pivoting for (Unsupervised) Entity Alignment. In AAAI. AAAI Press, Online, 4257–4266.
  40. Dangling-Aware Entity Alignment with Mixed High-Order Proximities. In NAACL-HLT (Findings). ACL, Seattle, WA, USA, 1172–1184.
  41. Boosting the Speed of Entity Alignment 10×: Dual Attention Matching Network with Normalized Hard Sample Mining. In WWW. ACM/IW3C2, Ljubljana, Slovenia, 821–832.
  42. Lazier than Lazy Greedy. In AAAI. AAAI Press, Austin, TX, USA, 1812–1818.
  43. Deep Learning for Entity Matching: A Design Space Exploration. In SIGMOD. ACM, Houston, TX, USA, 19–34.
  44. Active Deep Learning on Entity Resolution by Risk Sampling. Knowledge-Based System 236 (2022), 107729.
  45. Deep Sequence-to-Sequence Entity Matching for Heterogeneous Entity Resolution. In CIKM. ACM, Beijing, China, 629–638.
  46. Analyzing How BERT Performs Entity Matching. Proceedings of the VLDB Endowment 15, 8 (2022), 1726–1738.
  47. Progressive Duplicate Detection. IEEE Transactions on Knowledge and Data Engineering 27, 5 (2015), 1316–1329.
  48. Improving Cross-lingual Entity Alignment via Optimal Transport. In IJCAI. IJCAI, Macao, China, 3231–3237.
  49. A Survey of Deep Active Learning. ACM Computing Survey 54, 9 (2022), 180:1–180:40.
  50. PARIS: Probabilistic Alignment of Relations, Instances, and Schema. Proceedings of the VLDB Endowment 5, 3 (2011), 157–168.
  51. Knowing the No-match: Entity Alignment with Dangling Cases. In ACL-IJCNLP. ACL, Online, 3582–3593.
  52. RotatE: Knowledge Graph Embedding by Relational Rotation in Complex Space. In ICLR. OpenReview.net, New Orleans, LA, USA. https://openreview.net/forum?id=HkgEQnRqYQ
  53. Cross-Lingual Entity Alignment via Joint Attribute-Preserving Embedding. In ISWC. Springer, Vienna, Austria, 628–644.
  54. Bootstrapping Entity Alignment with Knowledge Graph Embedding. In IJCAI. IJCAI, Stockholm, Sweden, 4396–4402.
  55. Knowledge Graph Alignment Network with Gated Multi-Hop Neighborhood Aggregation. In AAAI. AAAI Press, New York, NY, USA, 222–229.
  56. A Benchmarking Study of Embedding-based Entity Alignment for Knowledge Graphs. Proceedings of the VLDB Endowment 13, 11 (2020), 2326–2340.
  57. YAGO 4: A Reason-able Knowledge Base. In ESWC. Springer, Heraklion, Greece, 583–596.
  58. Entity Alignment between Knowledge Graphs Using Attribute Embeddings. In AAAI. AAAI Press, Honolulu, HI, USA, 297–304.
  59. Composition-based Multi-Relational Graph Convolutional Networks. In ICLR. OpenReview.net, Addis Ababa, Ethiopia. https://openreview.net/forum?id=BylA_C4tPr
  60. Denny Vrandecic and Markus Krötzsch. 2014. Wikidata: A Free Collaborative Knowledgebase. Commun. ACM 57, 10 (2014), 78–85.
  61. Knowledge Graph Embedding: A Survey of Approaches and Applications. IEEE Transactions on Knowledge and Data Engineering 29, 12 (2017), 2724–2743.
  62. Cross-lingual Knowledge Graph Alignment via Graph Convolutional Networks. In EMNLP. ACL, Brussels, Belgium, 349–357.
  63. CorDEL: A Contrastive Deep Learning Approach for Entity Linkage. In ICDM. IEEE, Sorrento, Italy, 1322–1327.
  64. On Entity Alignment at Scale. The VLDB Journal 31, 5 (2022), 1009–1033.
  65. Collective Entity Alignment via Adaptive Features. In ICDE. IEEE, Dallas, TX, USA, 1870–1873.
  66. Multi-view Knowledge Graph Embedding for Entity Alignment. In IJCAI. IJCAI, Macao, China, 5429–5435.
  67. A Benchmark and Comprehensive Survey on Knowledge Graph Entity Alignment via Representation Learning. The VLDB Journal 31, 5 (2022), 1143–1168.
  68. An Experimental Study of State-of-the-Art Entity Alignment Approaches. IEEE Transactions on Knowledge and Data Engineering 34, 6 (2022), 2610–2625.
  69. Collective Multi-type Entity Alignment Between Knowledge Graphs. In WWW. ACM/IW3C2, Taipei, Taiwan, 2241–2252.
  70. PBA: Partition and Blocking Based Alignment for Large Knowledge Bases. In DASFAA. Springer, Dallas, TX, USA, 415–431.
  71. Hike: A Hybrid Human-Machine Method for Entity Alignment in Large-Scale Knowledge Bases. In CIKM. ACM, Singapore, 1917–1926.
Citations (10)
View on Semantic Scholar

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now