# From Features to Graphs: Exploring Graph Structures and Pairwise Interactions via GNNs

arXiv: https://arxiv.org/abs/2502.13471 · HTML: https://mlsanity.com/paper/2502.13471/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 15 of its 32 references that are in the map.
- First posted on arXiv 19 Feb 2025.

## Builds on (most cited first, 15 of 15)

- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Neural Machine Translation by Jointly Learning to Align and Translate](https://mlsanity.com/paper/1409.0473/) (2014)
- [DropEdge: Towards Deep Graph Convolutional Networks on Node Classification](https://mlsanity.com/paper/1907.10903/) (2019)
- [DeepFM: A Factorization-Machine based Neural Network for CTR Prediction](https://mlsanity.com/paper/1703.04247/) (2017)
- [Masked Label Prediction: Unified Message Passing Model for Semi-Supervised Classification](https://mlsanity.com/paper/2009.03509/) (2020)
- [Self-Attention Graph Pooling](https://mlsanity.com/paper/1904.08082/) (2019)
- [Deep & Cross Network for Ad Click Predictions](https://mlsanity.com/paper/1708.05123/) (2017)
- [Attentional Factorization Machines: Learning the Weight of Feature Interactions via Attention Networks](https://mlsanity.com/paper/1708.04617/) (2017)
- [Fi-GNN: Modeling Feature Interactions via Graph Neural Networks for CTR Prediction](https://mlsanity.com/paper/1910.05552/) (2019)
- [Adaptive Factorization Network: Learning Adaptive-Order Feature Interactions](https://mlsanity.com/paper/1909.03276/) (2019)
- [Towards Deeper, Lighter and Interpretable Cross Network for CTR Prediction](https://mlsanity.com/paper/2311.04635/) (2023)
- [GraphFM: Graph Factorization Machines for Feature Interaction Modeling](https://mlsanity.com/paper/2105.11866/) (2021)
- [Optimizing Feature Set for Click-Through Rate Prediction](https://mlsanity.com/paper/2301.10909/) (2023)
- [Explicit Feature Interaction-aware Graph Neural Networks](https://mlsanity.com/paper/2204.03225/) (2022)
- [AdnFM: An Attentive DenseNet based Factorization Machine for CTR Prediction](https://mlsanity.com/paper/2012.10820/) (2020)

## Abstract (arXiv)

Feature interaction is crucial in predictive machine learning models, as it captures the relationships between features that influence model performance. In this work, we focus on pairwise interactions and investigate their importance in constructing feature graphs for Graph Neural Networks (GNNs). We leverage existing GNN models and tools to explore the relationship between feature graph structures and their effectiveness in modeling interactions. Through experiments on synthesized datasets, we uncover that edges between interacting features are important for enabling GNNs to model feature interactions effectively. We also observe that including non-interaction edges can act as noise, degrading model performance. Furthermore, we provide theoretical support for sparse feature graph selection using the Minimum Description Length (MDL) principle. We prove that feature graphs retaining only necessary interaction edges yield a more efficient and interpretable representation than complete graphs, aligning with Occam's Razor. Our findings offer both theoretical insights and practical guidelines for designing feature graphs that improve the performance and interpretability of GNN models.