Graph Trees with Attention

by   Maya Bechler-Speicher, et al.

When dealing with tabular data, models based on regression and decision trees are a popular choice due to the high accuracy they provide on such tasks and their ease of application as compared to other model classes. Yet, when it comes to graph-structure data, current tree learning algorithms do not provide tools to manage the structure of the data other than relying on feature engineering. In this work we address the above gap, and introduce Graph Trees with Attention (GTA), a new family of tree-based learning algorithms that are designed to operate on graphs. GTA leverages both the graph structure and the features at the vertices and employs an attention mechanism that allows decisions to concentrate on sub-structures of the graph. We analyze GTA models and show that they are strictly more expressive than plain decision trees. We also demonstrate the benefits of GTA empirically on multiple graph and node prediction benchmarks. In these experiments, GTA always outperformed other tree-based models and often outperformed other types of graph-learning algorithms such as Graph Neural Networks (GNNs) and Graph Kernels. Finally, we also provide an explainability mechanism for GTA, and demonstrate it can provide intuitive explanations.


page 1

page 2

page 3

page 4


Improving the Validity of Decision Trees as Explanations

In classification and forecasting with tabular data, one often utilizes ...

DT+GNN: A Fully Explainable Graph Neural Network using Decision Trees

We propose the fully explainable Decision Tree Graph Neural Network (DT+...

Graph Neural Networks Use Graphs When They Shouldn't

Predictions over graphs play a crucial role in various domains, includin...

Geometric tree kernels: Classification of COPD from airway tree geometry

Methodological contributions: This paper introduces a family of kernels ...

Multi-view graph structure learning using subspace merging on Grassmann manifold

Many successful learning algorithms have been recently developed to repr...

CoulGAT: An Experiment on Interpretability of Graph Attention Networks

We present an attention mechanism inspired from definition of screened C...

Graph Structure from Point Clouds: Geometric Attention is All You Need

The use of graph neural networks has produced significant advances in po...

Please sign up or login with your details

Forgot password? Click here to reset