Stable Tuple Embeddings for Dynamic Databases
Jan Tönshoff, Neta Friedman, Martin Grohe, Benny Kimelfeld
Abstract
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.
Ask Lune
Know this paper in minutes, not an afternoon.
Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.
1 top-tier paper has cited it since. Know what they found before your reviewers do.
Lune can draw on
the full paper · the top-tier papers that cite it · related work
Free to start. No credit card required.
Lineage
Cited by top-tier papers1
Builds on1
Related papers
- Scalable Feature Learning on Huge Knowledge Graphs for Downstream Machine LearningFélix Lefebvre, Gaël VaroquauxNeurIPS 2025 · 1 citation
- TLogic: Temporal Logical Rules for Explainable Link Forecasting on Temporal Knowledge GraphsYushan Liu, Yunpu Ma, Marcel Hildebrandt, Mitchell Joblin et al.AAAI 2022 · 193 citations
- Towards Global-Topology Relation Graph for Inductive Knowledge Graph CompletionLing Ding, Lei Huang, Zhizhi Yu, Di Jin et al.AAAI 2025 · 8 citations
- TeRDy: Temporal Relation Dynamics through Frequency Decomposition for Temporal Knowledge Graph CompletionZiyang Liu, Chaokun WangACL 2025
- InGram: Inductive Knowledge Graph Embedding via Relation GraphsJaejun Lee, Chanyoung Chung, Joyce Jiyoung WhangICML 2023 · 83 citations
