# Benchmark and Best Practices for Biomedical Knowledge Graph Embeddings

arXiv: https://arxiv.org/abs/2006.13774 · HTML: https://mlsanity.com/paper/2006.13774/

## Key facts

- Cited by 21 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 24 Jun 2020.

## Built on by (most cited first, 21 of 21)

- [Scientific Language Models for Biomedical Knowledge Base Completion: An Empirical Study](https://mlsanity.com/paper/2106.09700/) (2021)
- [KCD: Knowledge Walks and Textual Cues Enhanced Political Perspective Detection in News Media](https://mlsanity.com/paper/2204.04046/) (2022)
- [Understanding the Performance of Knowledge Graph Embeddings in Drug Discovery](https://mlsanity.com/paper/2105.10488/) (2021)
- [Building Trustworthy NeuroSymbolic AI Systems: Consistency, Reliability, Explainability, and Safety](https://mlsanity.com/paper/2312.06798/) (2023)
- [Knowledge Crosswords: Geometric Knowledge Reasoning with Large Language Models](https://mlsanity.com/paper/2310.01290/) (2023)
- [KALM: Knowledge-Aware Integration of Local, Document, and Global Contexts for Long Document Understanding](https://mlsanity.com/paper/2210.04105/) (2022)
- [A Retrieval-Augmented Knowledge Mining Method with Deep Thinking LLMs for Biomedical Research and Clinical Support](https://mlsanity.com/paper/2503.23029/) (2025)
- [Low-Rank Subspaces for Unsupervised Entity Linking](https://mlsanity.com/paper/2104.08737/) (2021)
- [MedDistant19: Towards an Accurate Benchmark for Broad-Coverage Biomedical Relation Extraction](https://mlsanity.com/paper/2204.04779/) (2022)
- [Know2BIO: A Comprehensive Dual-View Benchmark for Evolving Biomedical Knowledge Graphs](https://mlsanity.com/paper/2310.03221/) (2023)
- [OntologyRAG: Better and Faster Biomedical Code Mapping with Retrieval-Augmented Generation (RAG) Leveraging Ontology Knowledge Graphs and Large Language Models](https://mlsanity.com/paper/2502.18992/) (2025)
- [BALI: Enhancing Biomedical Language Representations through Knowledge Graph and Language Model Alignment](https://mlsanity.com/paper/2509.07588/) (2025)
- [UMLS-KGI-BERT: Data-Centric Knowledge Integration in Transformers for Biomedical Entity Recognition](https://mlsanity.com/paper/2307.11170/) (2023)
- [Knowledge Graph Embeddings for Multi-Lingual Structured Representations of Radiology Reports](https://mlsanity.com/paper/2309.00917/) (2023)
- [KEEP: Integrating Medical Ontologies with Clinical Data for Robust Code Embeddings](https://mlsanity.com/paper/2510.05049/) (2025)
- [Fast Knowledge Graph Completion using Graphics Processing Units](https://mlsanity.com/paper/2307.12059/) (2023)
- [Development of a Knowledge Graph Embeddings Model for Pain](https://mlsanity.com/paper/2308.08904/) (2023)
- [Preserving Empirical Probabilities in BERT for Small-sample Clinical Entity Recognition](https://mlsanity.com/paper/2409.03238/) (2024)
- [SMART: Relation-Aware Learning of Geometric Representations for Knowledge Graphs](https://mlsanity.com/paper/2507.13001/) (2025)
- [LogosKG: Hardware-Optimized Scalable and Interpretable Knowledge Graph Retrieval](https://mlsanity.com/paper/2604.18913/) (2026)
- [Inferring Sensitive Attributes from Knowledge Graph Embeddings: Attack and Defense Strategies](https://mlsanity.com/paper/2605.19644/) (2026)

## Abstract (arXiv)

Much of biomedical and healthcare data is encoded in discrete, symbolic form such as text and medical codes. There is a wealth of expert-curated biomedical domain knowledge stored in knowledge bases and ontologies, but the lack of reliable methods for learning knowledge representation has limited their usefulness in machine learning applications. While text-based representation learning has significantly improved in recent years through advances in natural language processing, attempts to learn biomedical concept embeddings so far have been lacking. A recent family of models called knowledge graph embeddings have shown promising results on general domain knowledge graphs, and we explore their capabilities in the biomedical domain. We train several state-of-the-art knowledge graph embedding models on the SNOMED-CT knowledge graph, provide a benchmark with comparison to existing methods and in-depth discussion on best practices, and make a case for the importance of leveraging the multi-relational nature of knowledge graphs for learning biomedical knowledge representation. The embeddings, code, and materials will be made available to the communitY.