Training Free Graph Neural Networks for Graph Matching

TL;DR

This paper introduces a training-free framework for graph neural networks in graph matching, enabling fast, effective performance without training by incorporating handcrafted priors into GNN architecture.

Contribution

The authors propose a novel training-free approach, TFGM, that integrates handcrafted priors into GNNs for graph matching, applicable across supervised, semi-supervised, and unsupervised settings.

Findings

TFGM achieves comparable or better performance than trained GNNs.

TFGM is especially effective in unsupervised graph matching.

The framework is generalizable to various GNN architectures.

Abstract

We present a framework of Training Free Graph Matching (TFGM) to boost the performance of Graph Neural Networks (GNNs) based graph matching, providing a fast promising solution without training (training-free). TFGM provides four widely applicable principles for designing training-free GNNs and is generalizable to supervised, semi-supervised, and unsupervised graph matching. The keys are to handcraft the matching priors, which used to be learned by training, into GNN's architecture and discard the components inessential under the training-free setting. Further analysis shows that TFGM is a linear relaxation to the quadratic assignment formulation of graph matching and generalizes TFGM to a broad set of GNNs. Extensive experiments show that GNNs with TFGM achieve comparable (if not better) performances to their fully trained counterparts, and demonstrate TFGM's superiority in the unsupervised setting. Our code is available at https://github.com/acharkq/Training-Free-Graph-Matching.