# No Need to Train Your RDB Foundation Model arXiv: https://arxiv.org/abs/2602.13697 · HTML: https://mlsanity.com/paper/2602.13697/ ## Key facts - Cited by 10 papers in the map (data through 14 Oct 2026). - Builds on 49 of its 82 references that are in the map. - First posted on arXiv 14 Feb 2026. ## Builds on (most cited first, 30 of 49) - [XGBoost: A Scalable Tree Boosting System](https://mlsanity.com/paper/1603.02754/) (2016) - [Gemma 3 Technical Report](https://mlsanity.com/paper/2503.19786/) (2025) - [Modeling Relational Data with Graph Convolutional Networks](https://mlsanity.com/paper/1703.06103/) (2017) - [Revisiting Deep Learning Models for Tabular Data](https://mlsanity.com/paper/2106.11959/) (2021) - [DeepFM: A Factorization-Machine based Neural Network for CTR Prediction](https://mlsanity.com/paper/1703.04247/) (2017) - [TabPFN: A Transformer That Solves Small Tabular Classification Problems in a Second](https://mlsanity.com/paper/2207.01848/) (2022) - [Heterogeneous Graph Transformer](https://mlsanity.com/paper/2003.01332/) (2020) - [Principal Neighbourhood Aggregation for Graph Nets](https://mlsanity.com/paper/2004.05718/) (2020) - [AutoGluon-Tabular: Robust and Accurate AutoML for Structured Data](https://mlsanity.com/paper/2003.06505/) (2020) - [SAINT: Improved Neural Networks for Tabular Data via Row Attention and Contrastive Pre-Training](https://mlsanity.com/paper/2106.01342/) (2021) - [TabICL: A Tabular Foundation Model for In-Context Learning on Large Data](https://mlsanity.com/paper/2502.05564/) (2025) - [SIGN: Scalable Inception Graph Neural Networks](https://mlsanity.com/paper/2004.11198/) (2020) - [TabPFN-2.5: Advancing the State of the Art in Tabular Foundation Models](https://mlsanity.com/paper/2511.08667/) (2025) - [RelBench: A Benchmark for Deep Learning on Relational Databases](https://mlsanity.com/paper/2407.20060/) (2024) - [Relational Graph Attention Networks](https://mlsanity.com/paper/1904.05811/) (2019) - [Large Language Models Can Automatically Engineer Features for Few-Shot Tabular Learning](https://mlsanity.com/paper/2404.09491/) (2024) - [LimiX: Unleashing Structured-Data Modeling Capability for Generalist Intelligence](https://mlsanity.com/paper/2509.03505/) (2025) - [OpenGraph: Towards Open Graph Foundation Models](https://mlsanity.com/paper/2403.01121/) (2024) - [Mitra: Mixed Synthetic Priors for Enhancing Tabular Foundation Models](https://mlsanity.com/paper/2510.21204/) (2025) - [Statistical Foundations of Prior-Data Fitted Networks](https://mlsanity.com/paper/2305.11097/) (2023) - [Relational Deep Learning: Graph Representation Learning on Relational Databases](https://mlsanity.com/paper/2312.04615/) (2023) - [AnyGraph: Graph Foundation Model in the Wild](https://mlsanity.com/paper/2408.10700/) (2024) - [Position: Graph Learning Will Lose Relevance Due To Poor Benchmarks](https://mlsanity.com/paper/2502.14546/) (2025) - [Supervised Learning on Relational Databases with Graph Neural Networks](https://mlsanity.com/paper/2002.02046/) (2020) - [Griffin: Towards a Graph-Centric Relational Database Foundation Model](https://mlsanity.com/paper/2505.05568/) (2025) - [Relational Transformer: Toward Zero-Shot Foundation Models for Relational Data](https://mlsanity.com/paper/2510.06377/) (2025) - [Turning Tabular Foundation Models into Graph Foundation Models](https://mlsanity.com/paper/2508.20906/) (2025) - [Relational Graph Transformer](https://mlsanity.com/paper/2505.10960/) (2025) - [Large Language Models are Good Relational Learners](https://mlsanity.com/paper/2506.05725/) (2025) - [Relational Deep Learning: Challenges, Foundations and Next-Generation Architectures](https://mlsanity.com/paper/2506.16654/) (2025) ## Built on by (most cited first, 10 of 10) - [Beyond IID: How General Are Tabular Foundation Models, Really?](https://mlsanity.com/paper/2606.30410/) (2026) - [KumoRFM-2: Scaling Foundation Models for Relational Learning](https://mlsanity.com/paper/2604.12596/) (2026) - [Advancing Open and Reproducible Relational Learning: RelArena-α, TabPFN-Rel and RPI](https://mlsanity.com/paper/2608.16319/) (2026) - [RelAgent: LLM Agents as Data Scientists for Relational Learning](https://mlsanity.com/paper/2605.07840/) (2026) - [FlexTab: A Flexible Encoder-Decoder Architecture for In-Context Learning Across Diverse Tabular Tasks](https://mlsanity.com/paper/2606.30336/) (2026) - [InvWeaver: Deductive Feedback for Invariant Synthesis in Interacting-Loop Programs](https://mlsanity.com/paper/2607.05478/) (2026) - [The Universal Classifier for Graph Learning](https://mlsanity.com/paper/2609.36302/) (2026) - [STEER: Reducing Inference Cost in Relational Foundation Models through Semantically Informed Sampling](https://mlsanity.com/paper/2610.00907/) (2026) - [RelICL: Training-free Relational Learning with Tabular Foundation Models](https://mlsanity.com/paper/2610.01725/) (2026) - [Revisiting Simple Baselines for Relational Deep Learning](https://mlsanity.com/paper/2610.20534/) (2026) ## Abstract (arXiv) Relational databases (RDBs) contain vast amounts of heterogeneous tabular information that can be exploited for predictive modeling purposes. But since the space of potential targets is vast across enterprise settings, how can we avoid retraining a new model each time we wish to predict a new quantity of interest? Foundation models based on in-context learning (ICL) offer a convenient option, but so far are largely restricted to single-table operability. In generalizing to multiple interrelated tables, it is essential to compress variably-sized RDB neighborhoods into fixed-length ICL samples for consumption by the decoder. However, the details here are critical: unlike existing supervised learning RDB pipelines, we provide theoretical and empirical evidence that ICL-specific compression should be constrained within high-dimensional RDB columns where all entities share units and roles, not across columns where the relevance of heterogeneous data types cannot be determined without extensive label information. Conditioned on this restriction, we then demonstrate that encoder expressiveness is actually not compromised by excluding trainable parameters. Hence we arrive at a principled family of RDB encoders that can be seamlessly paired with already-existing single-table ICL foundation models, whereby no training or fine-tuning is required. From a practical standpoint, we develop scalable SQL primitives to implement the encoder stage, resulting in the easy-to-use open-source RDBLearn foundation model capable of robust performance on unseen datasets out of the box.