Diffusion-Induced Spatial Attention Overlapping Community Detection
Researchers present DISCO, using diffusion priors and sparse attention for overlapping community detection and network anomalies.
The paper introduces Diffusion-Induced Spatial Attention Community Detection (DISCO), combining an influence-spreading structural prior, sparse multi-head attention, and non-negative community-affiliation learning. A Bernoulli-Poisson edge-reconstruction objective supports overlapping communities from attributes, structure, or both. The authors report competitive results against graph convolutional and graph attention methods. A cybersecurity proof of concept uses changes between consecutive communication-network snapshots as an interpretable anomaly signal and highlights implicated devices.
- DISCO biases sparse attention using a diffusion-based structural prior.
- A Bernoulli-Poisson objective infers overlapping community affiliations.
- Benchmarks are competitive with graph convolutional and attention models.
- A proof of concept treats community changes as network anomaly signals.
From the original article
1 min read at arxiv.orgDetection of overlapping communities is essential for modelling networks in which nodes participate simultaneously in multiple structural or functional groups. Existing graph neural network approaches commonly rely on local message passing, which can obscure community boundaries through smoothing and limit the representation of structurally relevant long-range dependencies.
By Kosti Koistinen · arxiv.org
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.