mlsanityData to 14 Oct 2026

DsMtGCN: A Direction-sensitive Multi-task framework for Knowledge Graph Completion

arXiv 2306.10290 ↗First posted 17 Jun 2023cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

To solve the inherent incompleteness of knowledge graphs (KGs), numbers of knowledge graph completion (KGC) models have been proposed to predict missing links from known triples. Among those, several works have achieved more advanced results via exploiting the structure information on KGs with Graph Convolutional Networks (GCN). However, we observe that entity embeddings aggregated from neighbors in different directions are just simply averaged to complete single-tasks by existing GCN based models, ignoring the specific requirements of forward and backward sub-tasks. In this paper, we propose a Direction-sensitive Multi-task GCN (DsMtGCN) to make full use of the direction information, the multi-head self-attention is applied to specifically combine embeddings in different directions based on various entities and sub-tasks, the geometric constraints are imposed to adjust the distribution of embeddings, and the traditional binary cross-entropy loss is modified to reflect the triple uncertainty. Moreover, the competitive experiments results on several benchmark datasets verify the effectiveness of our model.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 27 of its 44 references that are in the map. First posted on arXiv 17 Jun 2023.

Builds on

27 of 44 references.

References · 27

  1. 2017Attention Is All You Needcited by 60,361
  2. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  3. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  4. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
  5. 2017Modeling Relational Data with Graph Convolutional Networkscited by 1,694
  6. 2014Embedding Entities and Relations for Learning and Inference in Knowledge Basescited by 932
  7. 2016Complex Embeddings for Simple Link Predictioncited by 902
  8. 2019RotatE: Knowledge Graph Embedding by Relational Rotation in Complex Spacecited by 898
  9. 2017Convolutional 2D Knowledge Graph Embeddingscited by 730
  10. 2016Cross-stitch Networks for Multi-task Learningcited by 467
  11. 2019Composition-based Multi-Relational Graph Convolutional Networkscited by 396
  12. 2019Multi-Task Deep Neural Networks for Natural Language Understandingcited by 350
15 more
  1. 2019KG-BERT: BERT for Knowledge Graph Completioncited by 324
  2. 2015Holographic Embeddings of Knowledge Graphscited by 181
  3. 2017A Novel Embedding Model for Knowledge Base Completion Based on Convolutional Neural Networkcited by 143
  4. 2017Encoding Sentences with Graph Convolutional Networks for Semantic Role Labelingcited by 137
  5. 2019Learning Attention-based Embeddings for Relation Prediction in Knowledge Graphscited by 125
  6. 2019Learning to Exploit Long-term Relational Dependencies in Knowledge Graphscited by 83
  7. 2019A Re-evaluation of Knowledge Graph Completion Methodscited by 73
  8. 2019Multi-Task Feature Learning for Knowledge Graph Enhanced Recommendationcited by 71
  9. 2013A Semantic Matching Energy Function for Learning with Multi-relational Datacited by 61
  10. 2019InteractE: Improving Convolution-based Knowledge Graph Embeddings by Increasing Feature Interactionscited by 58
  11. 2019Interaction Embeddings for Prediction and Explanation in Knowledge Graphscited by 40
  12. 2019CoKE: Contextualized Knowledge Graph Embeddingcited by 30
  13. 2020Multi-Task Learning for Dense Prediction Tasks: A Surveycited by 28
  14. 2015Neural Generative Question Answeringcited by 22
  15. 2016Probabilistic Reasoning via Deep Learning: Neural Association Modelscited by 20

Built on by

Not cited yet.