The Map Equation goes Neural

Christopher Blöcker, Chester Tan, Ingo Scholtes

Primary Area: learning on graphs and other geometries & topologies

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.

Keywords: community detection, unsupervised clustering, graph neural network

Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2024/AuthorGuide.

TL;DR: We formulate the map equation, an information-theoretic objective function for community detection, in differentiable tensor form and use soft cluster assignments to detect communities with (graph) neural networks.

Abstract:

Community detection and graph clustering are essential for unsupervised data exploration and understanding the high-level organisation of networked systems.
Recently, graph clustering has been highlighted as an under-explored primary task for graph neural networks.
While hierarchical graph pooling has been shown to improve performance in graph and node classification tasks, it performs poorly in identifying meaningful clusters.
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 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.
More specifically, 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.
We evaluate our approach experimentally using different neural network architectures for unsupervised clustering in synthetic and real data.
Our results show that our approach achieves competitive performance against baselines, naturally detects overlapping communities, and avoids over-partitioning sparse graphs.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors' identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Submission Number: 399