Boundary Degree as a Node-level Feature for Epidemic Scenario Identification in Agent-based Cascade Simulations
arXiv:2606.29596v1 Announce Type: cross Abstract: Characterizing the scenario underlying an epidemic from its disease cascade is an important task in simulation analytics. We propose boundary degree, the count of an infected node's contacts in the underlying contact network that were not infected, as a per-node cascade feature for this task. Through systematic ablation on realistic social contact networks of Tennessee and Virginia, we show that boundary degree alone improves scenario identification accuracy by 19%. Edge features, whose importance was observed empirically by prior work, consist
The paper focuses on advancing methods for epidemic scenario identification, a field seeing increased computational sophistication due to recent global health events and the availability of large-scale social network data.
Improved capabilities for identifying epidemic scenarios using node-level features can significantly enhance public health responses, resource allocation, and preparedness for future outbreaks.
This research introduces a novel, effective feature (boundary degree) for interpreting cascade simulations, leading to more accurate and efficient identification of epidemic patterns within complex networks.
- · Public Health Agencies
- · Epidemiologists
- · Simulation Analytics Developers
- · AI/Machine Learning Researchers
- · Traditional Static Epidemiological Models
More accurate predictive models for disease spread will emerge, improving resource deployment.
This could lead to new types of early warning systems for public health threats, leveraging fine-grained network data.
The methodology might be adapted for identifying cascade scenarios in other complex systems, such as financial contagions or information spread.
This signal links to a primary source. Continuum Brief monitors and indexes it as part of the live intelligence stream — we do not republish source content.
Read at arXiv cs.LG