The Map Equation Goes Neural: Mapping Network Flows with Graph Neural Networks

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Blöcker, Christopher, Tan, Chester, Scholtes, Ingo
Formato: Preprint
Publicado: 2023
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866913606473351168
author Blöcker, Christopher
Tan, Chester
Scholtes, Ingo
author_facet Blöcker, Christopher
Tan, Chester
Scholtes, Ingo
contents Community detection is an essential tool for unsupervised data exploration and revealing the organisational structure of networked systems. With a long history in network science, community detection typically relies on objective functions, optimised with custom-tailored search algorithms, but often without leveraging recent advances in deep learning. Recently, first works have started incorporating such objectives into loss functions for deep graph clustering and pooling. We consider the map equation, a popular information-theoretic objective function for unsupervised community detection, and express it in differentiable tensor form for optimisation through gradient descent. Our formulation turns the map equation compatible with any neural network architecture, enables end-to-end learning, incorporates node features, and chooses the optimal number of clusters automatically, all without requiring explicit regularisation. Applied to unsupervised graph clustering tasks, we achieve competitive performance against state-of-the-art deep graph clustering baselines in synthetic and real-world datasets.
format Preprint
id arxiv_https___arxiv_org_abs_2310_01144
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle The Map Equation Goes Neural: Mapping Network Flows with Graph Neural Networks
Blöcker, Christopher
Tan, Chester
Scholtes, Ingo
Machine Learning
Community detection is an essential tool for unsupervised data exploration and revealing the organisational structure of networked systems. With a long history in network science, community detection typically relies on objective functions, optimised with custom-tailored search algorithms, but often without leveraging recent advances in deep learning. Recently, first works have started incorporating such objectives into loss functions for deep graph clustering and pooling. We consider the map equation, a popular information-theoretic objective function for unsupervised community detection, and express it in differentiable tensor form for optimisation through gradient descent. Our formulation turns the map equation compatible with any neural network architecture, enables end-to-end learning, incorporates node features, and chooses the optimal number of clusters automatically, all without requiring explicit regularisation. Applied to unsupervised graph clustering tasks, we achieve competitive performance against state-of-the-art deep graph clustering baselines in synthetic and real-world datasets.
title The Map Equation Goes Neural: Mapping Network Flows with Graph Neural Networks
topic Machine Learning
url https://arxiv.org/abs/2310.01144