1. Learning graph edit distance by graph neural networks.
- Author
-
Riba, Pau, Fischer, Andreas, Lladós, Josep, and Fornés, Alicia
- Subjects
- *
DEEP learning , *MESSAGE passing (Computer science) , *DISTANCES , *ALGORITHMS , *DISTANCE education , *ARTIFICIAL neural networks - Abstract
• We adapt a traditional non-learnable GED algorithm to the novel paradigm of geometric deep learning. • Triplet network for learning graph distances by means of graph neural networks. • Learning distance in the graph domain without an embedding stage. • Graph-based keyword spotting application with state-of-the-art performance. The emergence of geometric deep learning as a novel framework to deal with graph-based representations has faded away traditional approaches in favor of completely new methodologies. In this paper, we propose a new framework able to combine the advances on deep metric learning with traditional approximations of the graph edit distance. Hence, we propose an efficient graph distance based on the novel field of geometric deep learning. Our method employs a message passing neural network to capture the graph structure, and thus, leveraging this information for its use on a distance computation. The performance of the proposed graph distance is validated on two different scenarios. On the one hand, in a graph retrieval of handwritten words i.e. keyword spotting, showing its superior performance when compared with (approximate) graph edit distance benchmarks. On the other hand, demonstrating competitive results for graph similarity learning when compared with the current state-of-the-art on a recent benchmark dataset. [ABSTRACT FROM AUTHOR]
- Published
- 2021
- Full Text
- View/download PDF