# Relational Database Distillation: From Structured Tables to Condensed Graph Data

arXiv: https://arxiv.org/abs/2510.06980 · HTML: https://mlsanity.com/paper/2510.06980/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 28 of its 50 references that are in the map.
- First posted on arXiv 8 Oct 2025.

## Builds on (most cited first, 28 of 28)

- [Inductive Representation Learning on Large Graphs](https://mlsanity.com/paper/1706.02216/) (2017)
- [How Powerful are Graph Neural Networks?](https://mlsanity.com/paper/1810.00826/) (2018)
- [Neural Message Passing for Quantum Chemistry](https://mlsanity.com/paper/1704.01212/) (2017)
- [Dynamic Graph CNN for Learning on Point Clouds](https://mlsanity.com/paper/1801.07829/) (2018)
- [Modeling Relational Data with Graph Convolutional Networks](https://mlsanity.com/paper/1703.06103/) (2017)
- [Heterogeneous Graph Attention Network](https://mlsanity.com/paper/1903.07293/) (2019)
- [Heterogeneous Graph Transformer](https://mlsanity.com/paper/2003.01332/) (2020)
- [Dataset Distillation by Matching Training Trajectories](https://mlsanity.com/paper/2203.11932/) (2022)
- [Efficient Dataset Distillation Using Random Feature Approximation](https://mlsanity.com/paper/2210.12067/) (2022)
- [RelBench: A Benchmark for Deep Learning on Relational Databases](https://mlsanity.com/paper/2407.20060/) (2024)
- [Scaling Up Graph Neural Networks Via Graph Coarsening](https://mlsanity.com/paper/2106.05150/) (2021)
- [A Survey on Graph Structure Learning: Progress and Opportunities](https://mlsanity.com/paper/2103.03036/) (2021)
- [Supervised Learning on Relational Databases with Graph Neural Networks](https://mlsanity.com/paper/2002.02046/) (2020)
- [RelGNN: Composite Message Passing for Relational Deep Learning](https://mlsanity.com/paper/2502.06784/) (2025)
- [A Review of Stochastic Block Models and Extensions for Graph Clustering](https://mlsanity.com/paper/1903.00114/) (2019)
- [Rethinking and Accelerating Graph Condensation: A Training-Free Approach with Class Partition](https://mlsanity.com/paper/2405.13707/) (2024)
- [Dancing with Still Images: Video Distillation via Static-Dynamic Disentanglement](https://mlsanity.com/paper/2312.00362/) (2023)
- [GFS: Graph-based Feature Synthesis for Prediction over Relational Databases](https://mlsanity.com/paper/2312.02037/) (2023)
- [Unveiling Vulnerabilities of Contrastive Recommender Systems to Poisoning Attacks](https://mlsanity.com/paper/2311.18244/) (2023)
- [ID-Free Not Risk-Free: LLM-Powered Agents Unveil Risks in ID-Free Recommender Systems](https://mlsanity.com/paper/2409.11690/) (2024)
- [Graph Condensation for Open-World Graph Learning](https://mlsanity.com/paper/2405.17003/) (2024)
- [Joint Relational Database Generation via Graph-Conditional Diffusion Models](https://mlsanity.com/paper/2505.16527/) (2025)
- [Contrastive Graph Condensation: Advancing Data Versatility through Self-Supervised Learning](https://mlsanity.com/paper/2411.17063/) (2024)
- [Graph Neural Networks for Databases: A Survey](https://mlsanity.com/paper/2502.12908/) (2025)
- [When Graph Contrastive Learning Backfires: Spectral Vulnerability and Defense in Recommendation](https://mlsanity.com/paper/2507.07436/) (2025)
- [A Thorough Performance Benchmarking on Lightweight Embedding-based Recommender Systems](https://mlsanity.com/paper/2406.17335/) (2024)
- [On-device Content-based Recommendation with Single-shot Embedding Pruning: A Cooperative Game Perspective](https://mlsanity.com/paper/2411.13052/) (2024)
- [Teaching MLPs to Master Heterogeneous Graph-Structured Knowledge for Efficient and Accurate Inference](https://mlsanity.com/paper/2411.14035/) (2024)

## Built on by (most cited first, 1 of 1)

- [Efficient Content-based Recommendation Model Training via Noise-aware Coreset Selection](https://mlsanity.com/paper/2601.10067/) (2026)

## Abstract (arXiv)

Relational databases (RDBs) underpin the majority of global data management systems, where information is structured into multiple interdependent tables. To effectively use the knowledge within RDBs for predictive tasks, recent advances leverage graph representation learning to capture complex inter-table relations as multi-hop dependencies. Despite achieving state-of-the-art performance, these methods remain hindered by the prohibitive storage overhead and excessive training time, due to the massive scale of the database and the computational burden of intensive message passing across interconnected tables. To alleviate these concerns, we propose and study the problem of Relational Database Distillation (RDD). Specifically, we aim to distill large-scale RDBs into compact heterogeneous graphs while retaining the predictive power (i.e., utility) required for training graph-based models. Multi-modal column information is preserved through node features, and primary-foreign key relations are encoded via heterogeneous edges, thereby maintaining both data fidelity and relational structure. To ensure adaptability across diverse downstream tasks without engaging the traditional, inefficient bi-level distillation framework, we further design a kernel ridge regression-guided objective with pseudo-labels, which produces quality features for the distilled graph. Extensive experiments on multiple real-world RDBs demonstrate that our solution substantially reduces the data size while maintaining competitive performance on classification and regression tasks, creating an effective pathway for scalable learning with RDBs.