# Stable Tuple Embeddings for Dynamic Databases

arXiv: https://arxiv.org/abs/2103.06766 · HTML: https://mlsanity.com/paper/2103.06766/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 11 Mar 2021.

## Built on by (most cited first, 5 of 5)

- [Selecting Walk Schemes for Database Embedding](https://mlsanity.com/paper/2401.11215/) (2024)
- [Database Views as Explanations for Relational Deep Learning](https://mlsanity.com/paper/2509.09482/) (2025)
- [Incorporating Deep Learning Design in Database Queries](https://mlsanity.com/paper/2605.24207/) (2026)
- [Beyond Single-Modal Analytics: A Framework for Integrating Heterogeneous LLM-Based Query Systems for Multi-Modal Data](https://mlsanity.com/paper/2602.01701/) (2026)
- [Neuro-Relational Programs: Unifying Queries and Neural Computation over Structured Data](https://mlsanity.com/paper/2606.11946/) (2026)

## Abstract (arXiv)

We study the problem of computing an embedding of the tuples of a relational database in a manner that is extensible to dynamic changes of the database. In this problem, the embedding should be stable in the sense that it should not change on the existing tuples due to the embedding of newly inserted tuples (as database applications might already rely on existing embeddings); at the same time, the embedding of all tuples, old and new, should retain high quality. This task is challenging since inter-dependencies among the embeddings of different entities are inherent in state-of-the-art embedding techniques for structured data. We study two approaches to solving the problem. The first is an adaptation of Node2Vec to dynamic databases. The second is the FoRWaRD algorithm (Foreign Key Random Walk Embeddings for Relational Databases) that draws from embedding techniques for general graphs and knowledge graphs, and is inherently utilizing the schema and its key and foreign-key constraints. We evaluate the embedding algorithms using a collection of downstream tasks of column prediction over geographical and biological domains. We find that in the traditional static setting, our two embedding methods achieve comparable results that are compatible with the state-of-the-art for the specific applications. In the dynamic setting, we find that the FoRWaRD algorithm generally outperforms and runs faster than the alternatives, and moreover, it features only a mild reduction of quality even when the database consists of more than half newly inserted tuples after the initial training of the embedding.