Combinatorial learning of graph edit distance via dynamic embedding

R Wang, T Zhang, T Yu, J Yan… - Proceedings of the IEEE …, 2021 - openaccess.thecvf.com
Abstract Graph Edit Distance (GED) is a popular similarity measurement for pairwise graphs
and it also refers to the recovery of the edit path from the source graph to the target graph …

Comparing heuristics for graph edit distance computation

DB Blumenthal, N Boria, J Gamper, S Bougleux… - The VLDB journal, 2020 - Springer
Because of its flexibility, intuitiveness, and expressivity, the graph edit distance (GED) is one
of the most widely used distance measures for labeled graphs. Since exactly computing …

Learning graph distances with message passing neural networks

P Riba, A Fischer, J Lladós… - 2018 24th International …, 2018 - ieeexplore.ieee.org
Graph representations have been widely used in pattern recognition thanks to their powerful
representation formalism and rich theoretical background. A number of error-tolerant graph …

Graph neural networks using local descriptions in attributed graphs: an application to symbol recognition and hand written character recognition

NI Kajla, MMS Missen, MM Luqman, M Coustaty - IEEE Access, 2021 - ieeexplore.ieee.org
Graph-based methods have been widely used by the document image analysis and
recognition community, as the different objects and the content in document images is best …

On the unification of the graph edit distance and graph matching problems

R Raveaux - Pattern Recognition Letters, 2021 - Elsevier
Error-tolerant graph matching gathers an important family of problems. These problems aim
at finding correspondences between two graphs while integrating an error model. In the …

Additive angular margin loss in deep graph neural network classifier for learning graph edit distance

NI Kajla, MMS Missen, MM Luqman, M Coustaty… - IEEE …, 2020 - ieeexplore.ieee.org
The recent success of graph neural networks (GNNs) in the area of pattern recognition (PR)
has increased the interest of researchers to use these frameworks in non-euclidean …

Approximate graph edit distance by several local searches in parallel

É Daller, S Bougleux, B Gaüzère, L Brun - 7th International Conference …, 2018 - hal.science
Solving or approximating the linear sum assignment problem (LSAP) is an important step of
several constructive and local search strategies developed to approximate the graph edit …

A parallel algorithm for subgraph isomorphism

V Carletti, P Foggia, P Ritrovato, M Vento… - … in Pattern Recognition …, 2019 - Springer
In different application fields, such as biology, databases, social networks and so on, graphs
are a widely adopted structure to represent the data. In these fields, a relevant problem is the …

Fast linear sum assignment with error-correction and no cost constraints

S Bougleux, B Gaüzère, DB Blumenthal… - Pattern Recognition Letters, 2020 - Elsevier
We propose an algorithm that efficiently solves the linear sum assignment problem with error-
correction and no cost constraints. This problem is encountered for instance in the …

Graph node matching for edit distance

A Moscatelli, J Piquenot, M Bérar, P Héroux… - Pattern Recognition …, 2024 - Elsevier
Graphs are commonly used to model interactions between elements of a set, but computing
the Graph Edit Distance between two graphs is an NP-complete problem that is particularly …