# From Features to Structure: Task-Aware Graph Construction for Relational and Tabular Learning with GNNs

arXiv: https://arxiv.org/abs/2506.02243 · HTML: https://mlsanity.com/paper/2506.02243/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 19 references that are in the map.
- First posted on arXiv 2 Jun 2025.

## Builds on (most cited first, 10 of 10)

- [Inductive Representation Learning on Large Graphs](https://mlsanity.com/paper/1706.02216/) (2017)
- [Fast Graph Representation Learning with PyTorch Geometric](https://mlsanity.com/paper/1903.02428/) (2019)
- [Modeling Relational Data with Graph Convolutional Networks](https://mlsanity.com/paper/1703.06103/) (2017)
- [Supervised Learning on Relational Databases with Graph Neural Networks](https://mlsanity.com/paper/2002.02046/) (2020)
- [Relational Graph Transformer](https://mlsanity.com/paper/2505.10960/) (2025)
- [TabGNN: Multiplex Graph Neural Network for Tabular Data Prediction](https://mlsanity.com/paper/2108.09127/) (2021)
- [Answering Conversational Questions on Structured Data without Logical Forms](https://mlsanity.com/paper/1908.11787/) (2019)
- [GFS: Graph-based Feature Synthesis for Prediction over Relational Databases](https://mlsanity.com/paper/2312.02037/) (2023)
- [Survey on Generalization Theory for Graph Neural Networks](https://mlsanity.com/paper/2503.15650/) (2025)
- [Graph Neural Networks for Tabular Data Learning: A Survey with Taxonomy and Directions](https://mlsanity.com/paper/2401.02143/) (2024)

## Built on by (most cited first, 6 of 6)

- [Grables: When Graph Structure Helps Tabular Prediction](https://mlsanity.com/paper/2602.03945/) (2026)
- [TabPrep: Closing the Feature Engineering Gap in Tabular Benchmarks](https://mlsanity.com/paper/2606.02384/) (2026)
- [Incorporating Deep Learning Design in Database Queries](https://mlsanity.com/paper/2605.24207/) (2026)
- [Hyperdimensional computing for structured querying on tabular data embeddings](https://mlsanity.com/paper/2606.13871/) (2026)
- [AutoGrable: What Is a Good Graph for a Table?](https://mlsanity.com/paper/2608.11431/) (2026)
- [No-Free-Graph: Learning When Multimodal Data Should Be Graphified](https://mlsanity.com/paper/2610.02768/) (2026)

## Abstract (arXiv)

Tabular and relational data remain the most ubiquitous formats in real-world machine learning applications, spanning domains from finance to healthcare. Although both formats offer structured representations, they pose distinct challenges for modern deep learning methods, which typically assume flat, feature-aligned inputs. Graph Neural Networks (GNNs) have emerged as a promising solution by capturing structural dependencies within and between tables. However, existing GNN-based approaches often rely on rigid, schema-derived graphs -- such as those based on primary-foreign key links -- thereby underutilizing rich, predictive signals in non key attributes. In this work, we introduce auGraph, a unified framework for task-aware graph augmentation that applies to both tabular and relational data. auGraph enhances base graph structures by selectively promoting attributes into nodes, guided by scoring functions that quantify their relevance to the downstream prediction task. This augmentation preserves the original data schema while injecting task-relevant structural signal. Empirically, auGraph outperforms schema-based and heuristic graph construction methods by producing graphs that better support learning for relational and tabular prediction tasks.