mlsanityData to 7 Oct 2026

Knowledge Graph Embedding with 3D Compound Geometric Transformations

arXiv 2304.00378 ↗First posted 1 Apr 2023cs.AI cs.LGcited by 3

Not on the map. Why?

Abstract (arXiv)

The cascade of 2D geometric transformations were exploited to model relations between entities in a knowledge graph (KG), leading to an effective KG embedding (KGE) model, CompoundE. Furthermore, the rotation in the 3D space was proposed as a new KGE model, Rotate3D, by leveraging its non-commutative property. Inspired by CompoundE and Rotate3D, we leverage 3D compound geometric transformations, including translation, rotation, scaling, reflection, and shear and propose a family of KGE models, named CompoundE3D, in this work. CompoundE3D allows multiple design variants to match rich underlying characteristics of a KG. Since each variant has its own advantages on a subset of relations, an ensemble of multiple variants can yield superior performance. The effectiveness and flexibility of CompoundE3D are experimentally verified on four popular link prediction datasets.

Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 43 of its 83 references that are in the map. First posted on arXiv 1 Apr 2023.

Builds on

43 of 83 references.

References · 43

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  3. 2016XGBoost: A Scalable Tree Boosting Systemcited by 5,120
  4. 2020Open Graph Benchmark: Datasets for Machine Learning on Graphscited by 2,148
  5. 2017Modeling Relational Data with Graph Convolutional Networkscited by 1,684
  6. 2016ConceptNet 5.5: An Open Multilingual Graph of General Knowledgecited by 1,065
  7. 2014Embedding Entities and Relations for Learning and Inference in Knowledge Basescited by 929
  8. 2016Complex Embeddings for Simple Link Predictioncited by 897
  9. 2019RotatE: Knowledge Graph Embedding by Relational Rotation in Complex Spacecited by 893
  10. 2017Convolutional 2D Knowledge Graph Embeddingscited by 729
  11. 2019KG-BERT: BERT for Knowledge Graph Completioncited by 323
  12. 2020Low-Dimensional Hyperbolic Knowledge Graph Embeddingscited by 195
31 more
  1. 2015Holographic Embeddings of Knowledge Graphscited by 181
  2. 2018RippleNet: Propagating User Preferences on the Knowledge Graph for Recommender Systemscited by 136
  3. 2019Learning Hierarchy-Aware Knowledge Graph Embeddings for Link Predictioncited by 133
  4. 2020Improving Conversational Recommender Systems via Knowledge Graph based Semantic Fusioncited by 122
  5. 2022SimKGC: Simple Contrastive Knowledge Graph Completion with Pre-trained Language Modelscited by 90
  6. 2017Analogical Inference for Multi-Relational Embeddingscited by 69
  7. 2020PairRE: Knowledge Graph Embeddings via Paired Relation Vectorscited by 67
  8. 2017Learning Symmetric Collaborative Dialogue Agents with Dynamic Knowledge Graph Embeddingscited by 59
  9. 2019InteractE: Improving Convolution-based Knowledge Graph Embeddings by Increasing Feature Interactionscited by 58
  10. 2017Knowledge Graph Embedding with Iterative Guidance from Soft Rulescited by 51
  11. 2021Relation Prediction as an Auxiliary Training Objective for Improving Multi-Relational Graph Representationscited by 37
  12. 2018Improving Knowledge Graph Embedding Using Simple Constraintscited by 36
  13. 2019AutoSF: Searching Scoring Functions for Knowledge Graph Embeddingcited by 34
  14. 2022Green Learning: Introduction, Examples and Outlookcited by 30
  15. 2019Relation Embedding with Dihedral Group in Knowledge Graphcited by 25
  16. 2020Multilingual Knowledge Graph Completion via Ensemble Knowledge Transfercited by 25
  17. 2022On Supervised Feature Selection from High Dimensional Feature Spacescited by 23
  18. 2021BiQUE: Biquaternionic Embeddings of Knowledge Graphscited by 19
  19. 2021Rot-Pro: Modeling Transitivity by Projection in Knowledge Graph Embeddingcited by 15
  20. 2020SEEK: Segmented Embedding of Knowledge Graphscited by 11
  21. 2020Knowledge Graph Embedding with Atrous Convolution and Residual Learningcited by 10
  22. 2021Hyperbolic Geometry is Not Necessary: Lightweight Euclidean-Based Models for Low-Dimensional Knowledge Graph Embeddingscited by 10
  23. 2021KGBoost: A Classification-based Knowledge Base Completion Method with Negative Samplingcited by 10
  24. 2021CORE: A Knowledge Graph Entity Type Prediction Method via Complex Space Regression and Embeddingcited by 10
  25. 2022CompoundE: Knowledge Graph Embedding with Translation, Rotation and Scaling Compound Operationscited by 10
  26. 2022TripleRE: Knowledge Graph Embeddings via Tripled Relation Vectorscited by 10
  27. 2022GreenKGC: A Lightweight Knowledge Graph Completion Methodcited by 9
  28. 2021Multiple Run Ensemble Learning with Low-Dimensional Knowledge Graph Embeddingscited by 8
  29. 2020DensE: An Enhanced Non-commutative Representation for Knowledge Graph Embedding with Adaptive Semantic Hierarchycited by 7
  30. 2022TranSHER: Translating Knowledge Graph Embedding with Hyper-Ellipsoidal Restrictioncited by 7
  31. 2022STaR: Knowledge Graph Embedding by Scaling, Translation and Rotationcited by 6

Built on by

Cited by year

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

3 papers.

  1. 2024Time Sensitive Knowledge Editing through Efficient Finetuningcited by 14
  2. 2023Knowledge Graph Embedding: An Overviewcited by 10
  3. 2025Two-dimensional Taxonomy for N-ary Knowledge Representation Learning Methodscited by 1