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.
Full article193 words · extracted from arxiv.org · click to collapse
Detection 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. We introduce Diffusion-Induced Spatial Attention Community Detection (DISCO), a deep-learning framework that combines a structural prior derived from influence spreading dynamics, sparse multi-head attention, and non-negative community-affiliation learning. The prior identifies candidate interactions beyond immediate graph neighbours and biases attention according to their structural proximity, while a Bernoulli-Poisson edge-reconstruction objective enables overlapping community inference from node attributes and structural profiles, or both. Benchmark experiments show that DISCO performs competitively against established graph convolutional and graph attention approaches across different input configurations. To demonstrate its practical applicability, we present a proof-of-concept cybersecurity use case in which changes between community assignments inferred from consecutive communication-network snapshots provide an interpretable anomaly signal. Temporal community similarity identifies structural deviations, while node-level contributions help locate the devices associated with them. DISCO therefore provides both a flexible method for overlapping community detection and a foundation for analysing structural change in dynamic networks.
Text extracted automatically; images, tables and formatting may be missing. Original: https://arxiv.org/abs/2609.26737