mlsanityData to 7 Oct 2026

Knowledge Base Completion: Baselines Strike Back

arXiv 1705.10744 ↗First posted 30 May 2017cs.LG cs.AIcited by 39

Not on the map. Why?

Abstract (arXiv)

Many papers have been published on the knowledge base completion task in the past few years. Most of these introduce novel architectures for relation learning that are evaluated on standard datasets such as FB15k and WN18. This paper shows that the accuracy of almost all models published on the FB15k can be outperformed by an appropriately tuned baseline - our reimplementation of the DistMult model. Our findings cast doubt on the claim that the performance improvements of recent models are due to architectural changes as opposed to hyper-parameter tuning or different training objectives. This should prompt future research to re-consider how the performance of models is evaluated and reported.

Key facts. Cited by 39 papers in the map (data through 7 Oct 2026). First posted on arXiv 30 May 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 14; 2022: 9; 2023: 8; 2024: 4; 2025: 2; 2026: 2.

39 papers.

Sort:

By area:

  1. 2021Accounting for Variance in Machine Learning Benchmarkscited by 195
  2. 2023Elo Uncovered: Robustness and Best Practices in Language Model Evaluationcited by 58
  3. 2021Randomness In Neural Network Training: Characterizing The Impact of Toolingcited by 57
  4. 2021Relation Prediction as an Auxiliary Training Objective for Improving Multi-Relational Graph Representationscited by 37
  5. 2021Role-Aware Modeling for N-ary Relational Knowledge Basescited by 29
  6. 2022HousE: Knowledge Graph Embedding with Householder Parameterizationcited by 29
  7. 2021Adversarial Attacks on Knowledge Graph Embeddings via Instance Attribution Methodscited by 16
  8. 2021Knowledge Hypergraph Embedding Meets Relational Algebracited by 10
  9. 2021Learning Embeddings from Knowledge Graphs With Numeric Edge Attributescited by 10
  10. 2022A Revealing Large-Scale Evaluation of Unsupervised Anomaly Detection Algorithmscited by 10
  11. 2022CARE: Certifiably Robust Learning with Reasoning via Variational Inferencecited by 10
  12. 2023Sem@K: Is my knowledge graph embedding model semantic-aware?cited by 10
27 more
  1. 2023Learning to Substitute Ingredients in Recipescited by 8
  2. 2021Unified Interpretation of Softmax Cross-Entropy and Negative Sampling: With Case Study for Knowledge Graph Embeddingcited by 7
  3. 2021GRAPE for Fast and Scalable Graph Processing and random walk-based Embeddingcited by 7
  4. 2022An Automatic Ontology Generation Framework with An Organizational Perspectivecited by 6
  5. 2022Geometric Algebra based Embeddings for Static and Temporal Knowledge Graph Completioncited by 6
  6. 2022Stay Positive: Knowledge Graph Embedding Without Negative Samplingcited by 5
  7. 2021Ranking vs. Classifying: Measuring Knowledge Base Completion Qualitycited by 4
  8. 2022KGxBoard: Explainable and Interactive Leaderboard for Evaluation of Knowledge Graph Completion Modelscited by 4
  9. 2021What is Learned in Knowledge Graph Embeddings?cited by 2
  10. 2021Prediction of Adverse Biological Effects of Chemicals Using Knowledge Graph Embeddingscited by 2
  11. 2023On The Fairness Impacts of Hardware Selection in Machine Learningcited by 2
  12. 2024KGExplainer: Towards Exploring Connected Subgraph Explanations for Knowledge Graph Completioncited by 2
  13. 2024A Survey on Knowledge Graph Structure and Knowledge Graph Embeddingscited by 2
  14. 2025Enhancing LLM Tool Use with High-quality Instruction Data from Knowledge Graphcited by 2
  15. 2021KGE-CL: Contrastive Learning of Tensor Decomposition Based Knowledge Graph Embeddingscited by 1
  16. 2022SpaceE: Knowledge Graph Embedding by Relational Linear Transformation in the Entity Spacecited by 1
  17. 2022Assessing the Effects of Hyperparameters on Knowledge Graph Embedding Qualitycited by 1
  18. 2023Can Persistent Homology provide an efficient alternative for Evaluation of Knowledge Graph Completion Methods?cited by 1
  19. 2023Temporal Smoothness Regularisers for Neural Link Predictorscited by 1
  20. 2025On the Theoretical Limitations of Embedding-based Link Predictioncited by 1
  21. 2021Scalable knowledge base completion with superposition memoriescited by 0
  22. 2023Fast Knowledge Graph Completion using Graphics Processing Unitscited by 0
  23. 2023Location Sensitive Embedding for Knowledge Graph Reasoningcited by 0
  24. 2024A Survey of Reasoning for Substitution Relationships: Definitions, Methods, and Directionscited by 0
  25. 2024Extending TWIG: Zero-Shot Predictive Hyperparameter Selection for KGEs based on Graph Structurecited by 0
  26. 2026FixV2W: Correcting Invalid CVE-CWE Mappings with Knowledge Graph Embeddingscited by 0
  27. 2026When Metrics Disagree: A Meta-Analysis of Knowledge-Graph-Completion Model Benchmarkingcited by 0