Berlin 2024 – scientific programme
Parts | Days | Selection | Search | Updates | Downloads | Help
SOE: Fachverband Physik sozio-ökonomischer Systeme
SOE 2: Focus Session: Machine Learning for Complex Socio-economic Systems
SOE 2.8: Talk
Monday, March 18, 2024, 11:45–12:00, MA 001
The Map Equation Goes Neural — Chester Tan1, Christopher Blöcker1, and •Ingo Scholtes1,2 — 1Chair of Machine Learning for Complex Networks, Center for Artificial Intelligence and Data Science, Julius-Maximilians-Universität Würzburg, Germany — 2Data Analytics Group, Department of Informatics, Zürich University, Switzerland
Community detection has a long history in network science, but typically relies on optimising objective functions with custom-tailored search algorithms, not leveraging recent advances in deep learning, particularly from graph neural networks. In this paper, we narrow this gap between the deep learning and network science communities. We consider the map equation, an information-theoretic objective function for unsupervised community detection. Expressing it in a fully differentiable tensor form that produces soft cluster assignments, we optimise the map equation with deep learning through gradient descent. The reformulated map equation is a loss function compatible with any graph neural network architecture, enabling flexible clustering and graph pooling that clusters both graph structure and data features in an end-to-end way, automatically finding an optimum number of clusters without explicit regularisation by following the minimum description length principle. Our results show that our approach achieves competitive performance against baselines, naturally detects overlapping communities, and avoids over-partitioning sparse graphs.
Keywords: Community Detection; Graph Clustering; Graph Neural Networks