# Duality-Induced Regularizer for Tensor Factorization Based Knowledge Graph Completion

arXiv: https://arxiv.org/abs/2011.05816 · HTML: https://mlsanity.com/paper/2011.05816/

## Key facts

- Cited by 28 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 11 Nov 2020.

## Built on by (most cited first, 28 of 28)

- [ConE: Cone Embeddings for Multi-Hop Reasoning over Knowledge Graphs](https://mlsanity.com/paper/2110.13715/) (2021)
- [Topology-Aware Correlations Between Relations for Inductive Link Prediction in Knowledge Graphs](https://mlsanity.com/paper/2103.03642/) (2021)
- [Knowledge Graph Contrastive Learning Based on Relation-Symmetrical Structure](https://mlsanity.com/paper/2211.10738/) (2022)
- [Rethinking Graph Convolutional Networks in Knowledge Graph Completion](https://mlsanity.com/paper/2202.05679/) (2022)
- [Multi-task Pre-training Language Model for Semantic Network Completion](https://mlsanity.com/paper/2201.04843/) (2022)
- [Joint Language Semantic and Structure Embedding for Knowledge Graph Completion](https://mlsanity.com/paper/2209.08721/) (2022)
- [Swift and Sure: Hardness-aware Contrastive Learning for Low-dimensional Knowledge Graph Embeddings](https://mlsanity.com/paper/2201.00565/) (2022)
- [Message Intercommunication for Inductive Relation Reasoning](https://mlsanity.com/paper/2305.14074/) (2023)
- [Duality-Induced Regularizer for Semantic Matching Knowledge Graph Embeddings](https://mlsanity.com/paper/2203.12949/) (2022)
- [KGTuner: Efficient Hyper-parameter Search for Knowledge Graph Learning](https://mlsanity.com/paper/2205.02460/) (2022)
- [Large Language Model Enhanced Knowledge Representation Learning: A Survey](https://mlsanity.com/paper/2407.00936/) (2024)
- [STaR: Knowledge Graph Embedding by Scaling, Translation and Rotation](https://mlsanity.com/paper/2202.07130/) (2022)
- [Rethinking Regularization Methods for Knowledge Graph Completion](https://mlsanity.com/paper/2505.23442/) (2025)
- [Knowledge Base Completion Meets Transfer Learning](https://mlsanity.com/paper/2108.13073/) (2021)
- [Neuron with Steady Response Leads to Better Generalization](https://mlsanity.com/paper/2111.15414/) (2021)
- [ER: Equivariance Regularizer for Knowledge Graph Completion](https://mlsanity.com/paper/2206.12142/) (2022)
- [DREAM: Adaptive Reinforcement Learning based on Attention Mechanism for Temporal Knowledge Graph Reasoning](https://mlsanity.com/paper/2304.03984/) (2023)
- [PALT: Parameter-Lite Transfer of Language Models for Knowledge Graph Completion](https://mlsanity.com/paper/2210.13715/) (2022)
- [KGE-CL: Contrastive Learning of Tensor Decomposition Based Knowledge Graph Embeddings](https://mlsanity.com/paper/2112.04871/) (2021)
- [FFHR: Fully and Flexible Hyperbolic Representation for Knowledge Graph Completion](https://mlsanity.com/paper/2302.04088/) (2023)
- [Self-Distillation with Meta Learning for Knowledge Graph Completion](https://mlsanity.com/paper/2305.12209/) (2023)
- [Knowledge Graph Completion by Intermediate Variables Regularization](https://mlsanity.com/paper/2506.02749/) (2025)
- [KG-BiLM: Knowledge Graph Embedding via Bidirectional Language Models](https://mlsanity.com/paper/2506.03576/) (2025)
- [Technical Report of Team GraphMIRAcles in the WikiKG90M-LSC Track of OGB-LSC @ KDD Cup 2021](https://mlsanity.com/paper/2107.05476/) (2021)
- [Learning Complete Topology-Aware Correlations Between Relations for Inductive Link Prediction](https://mlsanity.com/paper/2309.11528/) (2023)
- [Prior Bilinear Based Models for Knowledge Graph Completion](https://mlsanity.com/paper/2309.13834/) (2023)
- [Pre-training and Diagnosing Knowledge Base Completion Models](https://mlsanity.com/paper/2401.15439/) (2024)
- [RSCF: Relation-Semantics Consistent Filter for Entity Embedding of Knowledge Graph](https://mlsanity.com/paper/2505.20813/) (2025)

## Abstract (arXiv)

Tensor factorization based models have shown great power in knowledge graph completion (KGC). However, their performance usually suffers from the overfitting problem seriously. This motivates various regularizers -- such as the squared Frobenius norm and tensor nuclear norm regularizers -- while the limited applicability significantly limits their practical usage. To address this challenge, we propose a novel regularizer -- namely, DUality-induced RegulArizer (DURA) -- which is not only effective in improving the performance of existing models but widely applicable to various methods. The major novelty of DURA is based on the observation that, for an existing tensor factorization based KGC model (primal), there is often another distance based KGC model (dual) closely associated with it. Experiments show that DURA yields consistent and significant improvements on benchmarks.