mlsanityData to 7 Oct 2026

Robust Knowledge Graph Completion with Stacked Convolutions and a Student Re-Ranking Network

arXiv 2106.06555 ↗First posted 11 Jun 2021cs.LGcited by 11

Not on the map. Why?

Abstract (arXiv)

Knowledge Graph (KG) completion research usually focuses on densely connected benchmark datasets that are not representative of real KGs. We curate two KG datasets that include biomedical and encyclopedic knowledge and use an existing commonsense KG dataset to explore KG completion in the more realistic setting where dense connectivity is not guaranteed. We develop a deep convolutional network that utilizes textual entity representations and demonstrate that our model outperforms recent KG completion methods in this challenging setting. We find that our model's performance improvements stem primarily from its robustness to sparsity. We then distill the knowledge from the convolutional network into a student network that re-ranks promising candidate entities. This re-ranking stage leads to further improvements in performance and demonstrates the effectiveness of entity re-ranking for KG completion.

Key facts. Cited by 11 papers in the map (data through 7 Oct 2026). Builds on 34 of its 68 references that are in the map. First posted on arXiv 11 Jun 2021.

Builds on

34 of 68 references.

References · 34

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  3. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  4. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  5. 2015Distilling the Knowledge in a Neural Networkcited by 10,076
  6. 2016Densely Connected Convolutional Networkscited by 6,691
  7. 2015Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classificationcited by 3,590
  8. 2016Identity Mappings in Deep Residual Networkscited by 1,960
  9. 2019Language Models as Knowledge Bases?cited by 1,922
  10. 2020Domain-Specific Language Model Pretraining for Biomedical Natural Language Processingcited by 996
  11. 2019How Can We Know What Language Models Know?cited by 953
  12. 2014Embedding Entities and Relations for Learning and Inference in Knowledge Basescited by 929
22 more
  1. 2016Complex Embeddings for Simple Link Predictioncited by 897
  2. 2019RotatE: Knowledge Graph Embedding by Relational Rotation in Complex Spacecited by 893
  3. 2020A Primer in BERTology: What we know about how BERT workscited by 807
  4. 2019Passage Re-ranking with BERTcited by 629
  5. 2019Composition-based Multi-Relational Graph Convolutional Networkscited by 395
  6. 2019KG-BERT: BERT for Knowledge Graph Completioncited by 323
  7. 2019TuckER: Tensor Factorization for Knowledge Graph Completioncited by 290
  8. 2014Efficient Object Localization Using Convolutional Networkscited by 226
  9. 2015Holographic Embeddings of Knowledge Graphscited by 181
  10. 2019To Tune or Not to Tune? Adapting Pretrained Representations to Diverse Taskscited by 167
  11. 2017Learning from Noisy Labels with Distillationcited by 160
  12. 2018End-to-end Structure-Aware Convolutional Networks for Knowledge Base Completioncited by 136
  13. 2020Convolutional Networks with Dense Connectivitycited by 98
  14. 2019A Deep Look into Neural Ranking Models for Information Retrievalcited by 79
  15. 2017Analogical Inference for Multi-Relational Embeddingscited by 69
  16. 2019Commonsense Knowledge Base Completion with Structural and Semantic Contextcited by 61
  17. 2019InteractE: Improving Convolution-based Knowledge Graph Embeddings by Increasing Feature Interactionscited by 58
  18. 2014Question Answering with Subgraph Embeddingscited by 56
  19. 2018RESIDE: Improving Distantly-Supervised Neural Relation Extraction using Side Informationcited by 47
  20. 2014Open Question Answering with Weakly Supervised Embedding Modelscited by 26
  21. 2018Omnidirectional CNN for Visual Place Recognition and Navigationcited by 22
  22. 2016SSP: Semantic Space Projection for Knowledge Graph Embedding with Text Descriptionscited by 18

Built on by

Cited by year

Citing papers per year: 2021: 1; 2022: 5; 2023: 0; 2024: 4; 2025: 1.

11 papers.

  1. 2022Knowledge Is Flat: A Seq2Seq Generative Framework for Various Knowledge Graph Completioncited by 32
  2. 2022Multilingual Knowledge Graph Completion with Self-Supervised Adaptive Graph Alignmentcited by 24
  3. 2022Acquiring and Modelling Abstract Commonsense Knowledge via Conceptualizationcited by 17
  4. 2022InterHT: Knowledge Graph Embeddings by Interaction between Head and Tail Entitiescited by 6
  5. 2022Dense-ATOMIC: Towards Densely-connected ATOMIC with High Knowledge Coverage and Massive Multi-hop Pathscited by 6
  6. 2024The Integration of Semantic and Structural Knowledge in Knowledge Graph Entity Typingcited by 6
  7. 2024Large Language Model Enhanced Knowledge Representation Learning: A Surveycited by 6
  8. 2024Context Graphcited by 2
  9. 2021KGRefiner: Knowledge Graph Refinement for Improving Accuracy of Translational Link Prediction Methodscited by 1
  10. 2024KC-GenRe: A Knowledge-constrained Generative Re-ranking Method Based on Large Language Models for Knowledge Graph Completioncited by 1
  11. 2025KG-BiLM: Knowledge Graph Embedding via Bidirectional Language Modelscited by 1