# Knowledge Base Completion: Baseline strikes back (Again)

arXiv: https://arxiv.org/abs/2005.00804 · HTML: https://mlsanity.com/paper/2005.00804/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 2 May 2020.

## Built on by (most cited first, 12 of 12)

- [Relation Prediction as an Auxiliary Training Objective for Improving Multi-Relational Graph Representations](https://mlsanity.com/paper/2110.02834/) (2021)
- [A Multi-Task Perspective for Link Prediction with New Relation Types and Nodes](https://mlsanity.com/paper/2307.06046/) (2023)
- [How to Turn Your Knowledge Graph Embeddings into Generative Models](https://mlsanity.com/paper/2305.15944/) (2023)
- [Multilingual Knowledge Graph Completion with Joint Relation and Entity Alignment](https://mlsanity.com/paper/2104.08804/) (2021)
- [ReFactor GNNs: Revisiting Factorisation-based Models from a Message-Passing Perspective](https://mlsanity.com/paper/2207.09980/) (2022)
- [What is Learned in Knowledge Graph Embeddings?](https://mlsanity.com/paper/2110.09978/) (2021)
- [TWIG: Towards pre-hoc Hyperparameter Optimisation and Cross-Graph Generalisation via Simulated KGE Models](https://mlsanity.com/paper/2402.06097/) (2024)
- [Multi-level Shared Knowledge Guided Learning for Knowledge Graph Completion](https://mlsanity.com/paper/2405.06696/) (2024)
- [A Survey on Knowledge Graph Structure and Knowledge Graph Embeddings](https://mlsanity.com/paper/2412.10092/) (2024)
- [Can Persistent Homology provide an efficient alternative for Evaluation of Knowledge Graph Completion Methods?](https://mlsanity.com/paper/2301.12929/) (2023)
- [Temporal Smoothness Regularisers for Neural Link Predictors](https://mlsanity.com/paper/2309.09045/) (2023)
- [Extending TWIG: Zero-Shot Predictive Hyperparameter Selection for KGEs based on Graph Structure](https://mlsanity.com/paper/2412.14801/) (2024)

## Abstract (arXiv)

Knowledge Base Completion (KBC) has been a very active area lately. Several recent KBCpapers propose architectural changes, new training methods, or even new formulations. KBC systems are usually evaluated on standard benchmark datasets: FB15k, FB15k-237, WN18, WN18RR, and Yago3-10. Most existing methods train with a small number of negative samples for each positive instance in these datasets to save computational costs. This paper discusses how recent developments allow us to use all available negative samples for training. We show that Complex, when trained using all available negative samples, gives near state-of-the-art performance on all the datasets. We call this approach COMPLEX-V2. We also highlight how various multiplicative KBC methods, recently proposed in the literature, benefit from this train-ing regime and become indistinguishable in terms of performance on most datasets. Our work calls for a reassessment of their individual value, in light of these findings.