A Unified Framework for Interactive Visual Graph Matching via Attribute-Structure Synchronization

TL;DR

This paper introduces an interactive visual graph matching framework that combines attribute and structural information into a unified embedding space, enabling efficient and intuitive graph retrieval and exploration.

Contribution

It develops an attribute-structure synchronization method using CCA for unified embedding and provides interactive visual interfaces for graph matching and exploration.

Findings

Demonstrates superior graph matching accuracy on real datasets.

Enables fast, interactive graph retrieval with visual query interfaces.

Supports effective large graph exploration and validation.

Abstract

In traditional graph retrieval tools, graph matching is commonly used to retrieve desired graphs from extensive graph datasets according to their structural similarities. However, in real applications, graph nodes have numerous attributes which also contain valuable information for evaluating similarities between graphs. Thus, to achieve superior graph matching results, it is crucial for graph retrieval tools to make full use of the attribute information in addition to structural information. We propose a novel framework for interactive visual graph matching. In the proposed framework, an attribute-structure synchronization method is developed for representing structural and attribute features in a unified embedding space based on Canonical Correlation Analysis (CCA). To support fast and interactive matching, \revise{our method} provides users with intuitive visual query interfaces for traversing, filtering and searching for the target graph in the embedding space conveniently. With the designed interfaces, the users can also specify a new target graph with desired structural and semantic features. Besides, evaluation views are designed for easy validation and interpretation of the matching results. Case studies and quantitative comparisons on real-world datasets have demonstrated the superiorities of our proposed framework in graph matching and large graph exploration.