Learning Backbones: Sparsifying Graphs through Zero Forcing for Effective Graph-Based Learning

TL;DR

This paper presents a new graph sparsification method called learning backbones, using zero-forcing dynamics to create simplified graphs that retain essential learning features, leading to improved efficiency and performance in graph classification.

Contribution

The paper introduces a zero-forcing based framework for graph sparsification that preserves key learning properties, offering a novel approach to constructing effective learning backbones.

Findings

Outperforms existing sparsification techniques in classification accuracy

Reduces computational complexity while maintaining performance

Effective across multiple datasets and models

Abstract

This paper introduces a novel framework for graph sparsification that preserves the essential learning attributes of original graphs, improving computational efficiency and reducing complexity in learning algorithms. We refer to these sparse graphs as "learning backbones". Our approach leverages the zero-forcing (ZF) phenomenon, a dynamic process on graphs with applications in network control. The key idea is to generate a tree from the original graph that retains critical dynamical properties. By correlating these properties with learning attributes, we construct effective learning backbones. We evaluate the performance of our ZF-based backbones in graph classification tasks across eight datasets and six baseline models. The results demonstrate that our method outperforms existing techniques. Additionally, we explore extensions using node distance metrics to further enhance the framework's utility.