PA-GM: Position-Aware Learning of Embedding Networks for Deep Graph Matching

TL;DR

This paper introduces PA-GM, a neural network that enhances deep graph matching by incorporating position-aware features and relative node positioning, significantly improving accuracy in content matching tasks.

Contribution

It proposes a novel end-to-end neural network that maps graph matching into a high-dimensional space with position information, improving matching accuracy for similar content.

Findings

Outperforms baseline methods in graph matching accuracy

Effective in cross-category and real-world datasets

Demonstrates strong generalizability

Abstract

Graph matching can be formalized as a combinatorial optimization problem, where there are corresponding relationships between pairs of nodes that can be represented as edges. This problem becomes challenging when there are potential ambiguities present due to nodes and edges with high similarity, and there is a need to find accurate results for similar content matching. In this paper, we introduce a novel end-to-end neural network that can map the linear assignment problem into a high-dimensional space augmented with node-level relative position information, which is crucial for improving the method's performance for similar content matching. Our model constructs the anchor set for the relative position of nodes and then aggregates the feature information of the target node and each anchor node based on a measure of relative position. It then learns the node feature representation by integrating the topological structure and the relative position information, thus realizing the linear assignment between the two graphs. To verify the effectiveness and generalizability of our method, we conduct graph matching experiments, including cross-category matching, on different real-world datasets. Comparisons with different baselines demonstrate the superiority of our method. Our source code is available under https://github.com/anonymous.