The Zombie Infection Model
arXiv:2607.29409
2026
Architecture
2 ideas extracted · analyzed Aug 31, 2026
What the math gives to ML
The paper studies a continuous-time graph process in which infection spreads along infected-to-susceptible edges while infected nodes are removed at a rate proportional to their number of susceptible neighbors. This creates a competition between propagation and deletion, and shows that adding graph connectivity can reduce the probability of reaching a target. The transferable asset is an event-driven graph propagation mechanism with explicit excitatory and inhibitory transitions, together with a degree-aware routing principle that discourages harmful extra edges.
Ideas from this paper
Unverified
2026
Replace a conventional graph message-passing layer with a finite-horizon stochastic propagation process containing susceptible, infected, and removed feature states. Messages spread along active infected-to-susceptible edges, while infected nodes are simultaneously deleted at a rate proportional to their susceptible-neighbor count. This provides explicit propagation control and anti-oversmoothing dynamics instead of repeatedly averaging over every neighbor.
Useful6/10
Difficulty5/10
Novelty6/10
Unverified
2026
Use the model's non-monotonicity result to make graph connectivity a learned resource rather than assuming that every extra edge helps. An edge router assigns transmission scores but also charges a source-side collision cost for exposing an infected node to many susceptible neighbors. The resulting router can prune edges that increase competition and reduce useful reachability.
Useful5/10
Difficulty5/10
Novelty7/10