TREE-G: Decision Trees Contesting Graph Neural Networks

TL;DR

TREE-G introduces a novel decision tree model tailored for graph data, effectively combining topological and feature information, and demonstrating superior performance over existing graph learning methods.

Contribution

The paper presents TREE-G, a decision tree variant with a specialized split function and pointer mechanism for graph data, enhancing interpretability and predictive accuracy.

Findings

TREE-G outperforms other tree-based models on graph benchmarks.

TREE-G often surpasses GNNs and Graph Kernels in accuracy.

Models and predictions are explainable and visualizable.

Abstract

When dealing with tabular data, models based on decision trees are a popular choice due to their high accuracy on these data types, their ease of application, and explainability properties. However, when it comes to graph-structured data, it is not clear how to apply them effectively, in a way that incorporates the topological information with the tabular data available on the vertices of the graph. To address this challenge, we introduce TREE-G. TREE-G modifies standard decision trees, by introducing a novel split function that is specialized for graph data. Not only does this split function incorporate the node features and the topological information, but it also uses a novel pointer mechanism that allows split nodes to use information computed in previous splits. Therefore, the split function adapts to the predictive task and the graph at hand. We analyze the theoretical properties of TREE-G and demonstrate its benefits empirically on multiple graph and vertex prediction benchmarks. In these experiments, TREE-G consistently outperforms other tree-based models and often outperforms other graph-learning algorithms such as Graph Neural Networks (GNNs) and Graph Kernels, sometimes by large margins. Moreover, TREE-Gs models and their predictions can be explained and visualized