Random-Forest-Induced Graph Neural Networks for Tabular Learning

2026-02-27

AI Summary

This work addresses the challenge of applying graph neural networks (GNNs) to tabular data, which inherently lacks a graph structure. The authors propose a novel instance-level graph construction method that leverages the proximity between samples induced by random forests, thereby utilizing tree-based model outputs to define graph edges without imposing strong assumptions on the underlying feature geometry. This approach uniquely integrates the nonlinear feature interaction capabilities of random forests with the structural learning strengths of GNNs. Evaluated across 36 benchmark datasets, the method achieves significantly higher weighted F1 scores compared to established baselines and existing graph construction strategies, demonstrating both its effectiveness and robustness.

Technology Category

• Machine Learning: Graph-based Machine Learning
• Data Mining & Knowledge Management: Graph Mining, Social Network Analysis & Community
• Reasoning under Uncertainty: Graphical Models

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Graphs are essential for modeling complex relationships and capturing structured interactions in data. Graph Neural Networks (GNNs) are particularly effective when such relational structure is explicitly available, but many real-world datasets, most notably tabular data, lack an inherent graph representation. To address this limitation, we propose RF-GNN, a framework that constructs instance-level graphs from tabular data using proximity measures induced by random forests. These proximities capture nonlinear feature interactions and data-adaptive similarity without imposing restrictive assumptions on feature geometry. The resulting graphs enable the direct application of GNNs to tabular learning problems. Extensive experiments on 36 benchmark datasets demonstrate that RF-GNN consistently outperforms strong classical baselines and recent graph-construction methods in terms of weighted F1-score. Additional ablation studies highlight the impact of proximity design choices and graph construction settings.

Problem

• Graph Neural Networks
• Tabular Data
• Graph Construction
• Random Forest
• Structured Learning

Innovation

• Random Forest
• Graph Neural Networks
• Tabular Data
• Proximity-based Graph Construction
• Instance-level Graph