mlsanityData to 7 Oct 2026

Are Negative Samples Necessary in Entity Alignment? An Approach with High Performance, Scalability and Robustness

arXiv 2108.05278 ↗First posted 11 Aug 2021cs.AI cs.IRcited by 9

Not on the map. Why?

Abstract (arXiv)

Entity alignment (EA) aims to find the equivalent entities in different KGs, which is a crucial step in integrating multiple KGs. However, most existing EA methods have poor scalability and are unable to cope with large-scale datasets. We summarize three issues leading to such high time-space complexity in existing EA methods: (1) Inefficient graph encoders, (2) Dilemma of negative sampling, and (3) "Catastrophic forgetting" in semi-supervised learning. To address these challenges, we propose a novel EA method with three new components to enable high Performance, high Scalability, and high Robustness (PSR): (1) Simplified graph encoder with relational graph sampling, (2) Symmetric negative-free alignment loss, and (3) Incremental semi-supervised learning. Furthermore, we conduct detailed experiments on several public datasets to examine the effectiveness and efficiency of our proposed method. The experimental results show that PSR not only surpasses the previous SOTA in performance but also has impressive scalability and robustness.

Key facts. Cited by 9 papers in the map (data through 7 Oct 2026). Builds on 33 of its 49 references that are in the map. First posted on arXiv 11 Aug 2021.

Builds on

33 of 49 references.

References · 33

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 11,979
  3. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  4. 2017Graph Attention Networkscited by 8,854
  5. 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,482
  6. 2017Inductive Representation Learning on Large Graphscited by 6,284
  7. 2020Bootstrap your own latent: A new approach to self-supervised Learningcited by 4,712
  8. 2020Exploring Simple Siamese Representation Learningcited by 2,853
  9. 2015FaceNet: A Unified Embedding for Face Recognition and Clusteringcited by 2,833
  10. 2017Modeling Relational Data with Graph Convolutional Networkscited by 1,684
  11. 2015Fast and Accurate Deep Network Learning by Exponential Linear Units (ELUs)cited by 1,061
  12. 2019GraphSAINT: Graph Sampling Based Inductive Learning Methodcited by 618
21 more
  1. 2018FastGCN: Fast Learning with Graph Convolutional Networks via Importance Samplingcited by 583
  2. 2019Cluster-GCN: An Efficient Algorithm for Training Deep and Large Graph Convolutional Networkscited by 540
  3. 2017Word Translation Without Parallel Datacited by 480
  4. 2019Graph Matching Networks for Learning the Similarity of Graph Structured Objectscited by 202
  5. 2016Multilingual Knowledge Graph Embeddings for Cross-lingual Knowledge Alignmentcited by 128
  6. 2017Cross-lingual Entity Alignment via Joint Attribute-Preserving Embeddingcited by 126
  7. 2019Relation-Aware Entity Alignment for Heterogeneous Knowledge Graphscited by 106
  8. 2019Knowledge Graph Alignment Network with Gated Multi-hop Neighborhood Aggregationcited by 101
  9. 2019Unifying Knowledge Graph Learning and Recommendation: Towards a Better Understanding of User Preferencescited by 87
  10. 2019Multi-Channel Graph Neural Network for Entity Alignmentcited by 86
  11. 2020Deep Graph Matching Consensuscited by 85
  12. 2019Learning to Exploit Long-term Relational Dependencies in Knowledge Graphscited by 83
  13. 2019Multi-Task Feature Learning for Knowledge Graph Enhanced Recommendationcited by 70
  14. 2019Cross-lingual Knowledge Graph Alignment via Graph Matching Neural Networkcited by 68
  15. 2020Relational Reflection Entity Alignmentcited by 53
  16. 2017Learning with Average Top-k Losscited by 52
  17. 2019Aligning Cross-Lingual Entities with Multi-Aspect Informationcited by 46
  18. 2020TransEdge: Translating Relation-contextualized Embeddings for Knowledge Graphscited by 41
  19. 2019Jointly Learning Entity and Relation Representations for Entity Alignmentcited by 39
  20. 2020Knowledge Association with Hyperbolic Knowledge Graph Embeddingscited by 31
  21. 2021Complex Factoid Question Answering with a Free-Text Knowledge Graphcited by 14

Built on by

Cited by year

Citing papers per year: 2022: 4; 2023: 0; 2024: 4; 2025: 1.

9 papers.

  1. 2024Two Heads Are Better Than One: Integrating Knowledge from Knowledge Graphs and Large Language Models for Entity Alignmentcited by 8
  2. 2022Interactive Contrastive Learning for Self-supervised Entity Alignmentcited by 7
  3. 2022Joint Multilingual Knowledge Graph Completion and Alignmentcited by 3
  4. 2022Guiding Neural Entity Alignment with Compatibilitycited by 2
  5. 2022Dependency-aware Self-training for Entity Alignmentcited by 2
  6. 2024Aligning Multiple Knowledge Graphs in a Single Passcited by 2
  7. 2024Resilience in Knowledge Graph Embeddingscited by 1
  8. 2024Understanding and Guiding Weakly Supervised Entity Alignment with Potential Isomorphism Propagationcited by 0
  9. 2025Unsupervised Entity Alignment Based on Personalized Discriminative Rooted Treecited by 0