# MetaRTL: Meta-path Attention Enhanced Relational Table Learning

arXiv: https://arxiv.org/abs/2609.19832 · HTML: https://mlsanity.com/paper/2609.19832/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 19 of its 29 references that are in the map.
- First posted on arXiv 17 Sep 2026.

## Builds on (most cited first, 19 of 19)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Neural Message Passing for Quantum Chemistry](https://mlsanity.com/paper/1704.01212/) (2017)
- [Deeper Insights into Graph Convolutional Networks for Semi-Supervised Learning](https://mlsanity.com/paper/1801.07606/) (2018)
- [Revisiting Deep Learning Models for Tabular Data](https://mlsanity.com/paper/2106.11959/) (2021)
- [Heterogeneous Graph Attention Network](https://mlsanity.com/paper/1903.07293/) (2019)
- [Deep Neural Networks and Tabular Data: A Survey](https://mlsanity.com/paper/2110.01889/) (2021)
- [Simple and Efficient Heterogeneous Graph Neural Network](https://mlsanity.com/paper/2207.02547/) (2022)
- [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)
- [Trompt: Towards a Better Deep Neural Network for Tabular Data](https://mlsanity.com/paper/2305.18446/) (2023)
- [Database Meets Deep Learning: Challenges and Opportunities](https://mlsanity.com/paper/1906.08986/) (2019)
- [Zero-shot Node Classification with Decomposed Graph Prototype Network](https://mlsanity.com/paper/2106.08022/) (2021)
- [Graph Transformers for Large Graphs](https://mlsanity.com/paper/2312.11109/) (2023)
- [Boosting Relational Deep Learning with Pretrained Tabular Models](https://mlsanity.com/paper/2504.04934/) (2025)
- [rLLM: Relational Table Learning with LLMs](https://mlsanity.com/paper/2407.20157/) (2024)
- [From Cluster Assumption to Graph Convolution: Graph-based Semi-Supervised Learning Revisited](https://mlsanity.com/paper/2309.13599/) (2023)
- [LakeMLB: Data Lake Machine Learning Benchmark](https://mlsanity.com/paper/2602.10441/) (2026)
- [TLSQL: Table Learning Structured Query Language](https://mlsanity.com/paper/2601.14109/) (2026)

## Abstract (arXiv)

Relational table learning has gained increasing attention with the widespread use of relational databases. Existing methods typically rely on deep GNN or HGNN stacks, leading to high computational costs and limited performance on large real-world databases. We propose MetaRTL, a two-stage framework for scalable and expressive relational table learning. In the first stage, MetaRTL obtains initial table embeddings via lightweight pre-training. In the second stage, it performs non-parametric message passing to derive meta-path features, which are then aggregated by an attention module, MetaAttn. By shifting computation from deep message passing to efficient meta-path aggregation, MetaRTL captures rich relational semantics while maintaining high efficiency. Experiments on 10 real-world datasets across 24 tasks demonstrate the effectiveness of the proposed method.