A Multi-agent Approach for Graph Classification

Luca Baldini, Antonello Rizzi

2021

Abstract

In this paper, we propose and discuss a prototypical framework for graph classification. The proposed algorithm (Graph E-ABC) exploits a multi-agent design, where swarm of agents (orchestrated via evolutionary optimization) are in charge of finding meaningful substructures from the training data. The resulting set of substructures compose the pivotal entities for a graph embedding procedure that allows to move the pattern recognition problem from the graph domain towards the Euclidean space. In order to improve the learning capabilities, the pivotal substructures undergo an independent optimization procedure. The performances of Graph E-ABC are addressed via a sensitivity analysis over its critical parameters and compared against current approaches for graph classification. Results on five open access datasets of fully labelled graphs show interesting performances in terms of accuracy, counterbalanced by a relatively high number of pivotal substructures.

Paper Citation

in Harvard Style

Baldini L. and Rizzi A. (2021). A Multi-agent Approach for Graph Classification. In Proceedings of the 13th International Joint Conference on Computational Intelligence (IJCCI 2021) - Volume 1: NCTA; ISBN 978-989-758-534-0, SciTePress, pages 334-343. DOI: 10.5220/0010677300003063

in Bibtex Style

@conference{ncta21,
author={Luca Baldini and Antonello Rizzi},
title={A Multi-agent Approach for Graph Classification},
booktitle={Proceedings of the 13th International Joint Conference on Computational Intelligence (IJCCI 2021) - Volume 1: NCTA},
year={2021},
pages={334-343},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0010677300003063},
isbn={978-989-758-534-0},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 13th International Joint Conference on Computational Intelligence (IJCCI 2021) - Volume 1: NCTA
TI - A Multi-agent Approach for Graph Classification
SN - 978-989-758-534-0
AU - Baldini L.
AU - Rizzi A.
PY - 2021
SP - 334
EP - 343
DO - 10.5220/0010677300003063
PB - SciTePress