Attributed Graph Matching via Seeds Guiding

Abstract

Non-member Yali Zheng a , Non-member Attributed graph is a typical class of graphs with a set of attributes on nodes, edges, even high-order structure. Objects in the fields are naturally represented as attributed graphs with considerable noise and a large number of nodes, which make traditional graphs matching techniques confront with some new challenges, such as optimization difficulty, inability to match and so on. In order to solve these problems, we propose a new approach, called Attributed Graph Matching via Seeds Guiding (AGM-SG) in this paper. Our approach introduces seed nodes to guide attributed graph matching, and considers explicitly the first-order characteristics difference in the problem formulation. It is formulated as a quadratic optimization, and solved by Frank-Wolfe algorithm with continuous relaxation. It only has O(n 2 ) space complexity, and is suitable to apply to super-large graphs under different types. We evaluate the proposed approach on the synthetic dataset and three different real datasets including Wikipedia dataset, Enron mail dataset, and Caenorhabditis elegans dataset. Compared with the existing graph matching algorithms, the proposed algorithm outperforms original SGM, RGM and AGMLG significantly, which has more than 5% matching accuracy improvement on all datasets.