# Updating Embeddings for Dynamic Knowledge Graphs

arXiv: https://arxiv.org/abs/2109.10896 · HTML: https://mlsanity.com/paper/2109.10896/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 7 of its 25 references that are in the map.
- First posted on arXiv 22 Sep 2021.

## Builds on (most cited first, 7 of 7)

- [Embedding Entities and Relations for Learning and Inference in Knowledge Bases](https://mlsanity.com/paper/1412.6575/) (2014)
- [Complex Embeddings for Simple Link Prediction](https://mlsanity.com/paper/1606.06357/) (2016)
- [Holographic Embeddings of Knowledge Graphs](https://mlsanity.com/paper/1510.04935/) (2015)
- [Motifs in Temporal Networks](https://mlsanity.com/paper/1612.09259/) (2016)
- [Bringing Light Into the Dark: A Large-scale Evaluation of Knowledge Graph Embedding Models Under a Unified Framework](https://mlsanity.com/paper/2006.13365/) (2020)
- [Analogical Inference for Multi-Relational Embeddings](https://mlsanity.com/paper/1705.02426/) (2017)
- [The Anatomy of a Scientific Rumor](https://mlsanity.com/paper/1301.2952/) (2013)

## Built on by (most cited first, 4 of 4)

- [Multi-Head RAG: Solving Multi-Aspect Problems with LLMs](https://mlsanity.com/paper/2406.05085/) (2024)
- [Affordable AI Assistants with Knowledge Graph of Thoughts](https://mlsanity.com/paper/2504.02670/) (2025)
- [GraphSeek: Next-Generation Graph Analytics with LLMs](https://mlsanity.com/paper/2602.11052/) (2026)
- [Improving Continual Learning of Knowledge Graph Embeddings via Informed Initialization](https://mlsanity.com/paper/2511.11118/) (2025)

## Abstract (arXiv)

Data in Knowledge Graphs often represents part of the current state of the real world. Thus, to stay up-to-date the graph data needs to be updated frequently. To utilize information from Knowledge Graphs, many state-of-the-art machine learning approaches use embedding techniques. These techniques typically compute an embedding, i.e., vector representations of the nodes as input for the main machine learning algorithm. If a graph update occurs later on -- specifically when nodes are added or removed -- the training has to be done all over again. This is undesirable, because of the time it takes and also because downstream models which were trained with these embeddings have to be retrained if they change significantly. In this paper, we investigate embedding updates that do not require full retraining and evaluate them in combination with various embedding models on real dynamic Knowledge Graphs covering multiple use cases. We study approaches that place newly appearing nodes optimally according to local information, but notice that this does not work well. However, we find that if we continue the training of the old embedding, interleaved with epochs during which we only optimize for the added and removed parts, we obtain good results in terms of typical metrics used in link prediction. This performance is obtained much faster than with a complete retraining and hence makes it possible to maintain embeddings for dynamic Knowledge Graphs.