Informace o publikaci

Deep Learning Attention Model for Supervised and Unsupervised Network Community Detection

Logo poskytovatele
Autoři

SOBOLEVSKY Stanislav

Rok publikování 2023
Druh Článek ve sborníku
Konference Computational Science – ICCS 2023
Fakulta / Pracoviště MU

Přírodovědecká fakulta

Citace
www https://link.springer.com/chapter/10.1007/978-3-031-36027-5_51
Doi http://dx.doi.org/10.1007/978-3-031-36027-5_51
Klíčová slova Complex networks; Community detection; Deep Learning; Graph Neural Networks
Popis Network community detection is a complex problem that has to utilize heuristic approaches. It often relies on optimizing partition quality functions, such as modularity, description length, stochastic block-model likelihood etc. However, direct application of the traditional optimization methods has limited efficiency in finding the global maxima in such tasks. This paper proposes a novel bi-partite attention graph neural network model for supervised and unsupervised network community detection, suitable for unsupervised optimization of arbitrary partition quality functions, as well as for minimization of a loss function against the provided partition in a supervised setting. The model is demonstrated to be helpful in the unsupervised improvement of suboptimal partitions previously obtained by other known methods like Louvain algorithm for some of the classic and synthetic networks. It is also shown to be efficient in supervised learning of the provided community structure for a set of classic and synthetic networks. Furthermore, the paper serves as a proof-of-concept for the broader application of graph neural network models to unsupervised network optimization.
Související projekty:

Používáte starou verzi internetového prohlížeče. Doporučujeme aktualizovat Váš prohlížeč na nejnovější verzi.

Další info