DeepSIM: a novel deep learning method for graph similarity computation

Loading...
Thumbnail Image
Date
2024-01
Open Access Location
Journal Title
Journal ISSN
Volume Title
Publisher
Springer-Verlag GmbH
Rights
(c) 2023 The Author/s
CC BY 4.0
Abstract
Abstract: Graphs are widely used to model real-life information, where graph similarity computation is one of the most significant applications, such as inferring the properties of a compound based on similarity to a known group. Definition methods (e.g., graph edit distance and maximum common subgraph) have extremely high computational cost, and the existing efficient deep learning methods suffer from the problem of inadequate feature extraction which would have a bad effect on similarity computation. In this paper, a double-branch model called DeepSIM was raised to deeply mine graph-level and node-level features to address the above problems. On the graph-level branch, a novel embedding relational reasoning network was presented to obtain interaction between pairwise inputs. Meanwhile, a new local-to-global attention mechanism is designed to improve the capability of CNN-based node-level feature extraction module on another path. In DeepSIM, double-branch outputs will be concatenated as the final feature. The experimental results demonstrate that our methods perform well on several datasets compared to the state-of-the-art deep learning models in related fields.
Description
Keywords
Deep learning, Graph similarity, Embedding relational reasoning, Double branch
Citation
Liu B, Wang Z, Zhang J, Wu J, Qu G. (2024). DeepSIM: a novel deep learning method for graph similarity computation. Soft Computing. 28. 1. (pp. 61-76).
Collections