# Competing Infection-Removal Graph Layer

- ID: 1596
- Canonical URL: https://synthcore.org/idea/1596/competing-infection-removal-graph-layer
- API JSON: https://synthcore.org/api/idea/1596.json
- API Markdown: https://synthcore.org/api/idea/1596.md
- Verification status: unverified
- Source: [arXiv:2607.29409](https://arxiv.org/abs/2607.29409)
- Category: architecture
- Solves: accuracy, stability, generalization
- ML areas: graph-nn, regularization
- Math tags: stochastic-processes, probability, graph-theory, dynamical-systems
- Ratings: usefulness 6/10; difficulty 5/10; novelty 6/10

## Idea description

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.

## Mathematical statement

The paper defines the Zombie Infection Model generator as $$L_{\lambda,\mu}^{\mathrm{ZIM}}f(\omega)=\sum_{x:\omega(x)=I}\left(\mu\sum_{y:\omega(y)=S,\,x\sim y}[f(\omega^{x\leftarrow R})-f(\omega)]+\lambda\sum_{y:\omega(y)=S,\,x\sim y}[f(\omega^{y\leftarrow I})-f(\omega)]\right).$$ Here $G=(V,E)$ is a graph, $\omega:V    o\{S,I,R\}$ is the node-state configuration, $x\sim y$ means that $x$ and $y$ are adjacent, $\lambda>0$ is infection intensity per active SI edge, $\mu>0$ is removal intensity per susceptible neighbor, and $\omega^{z\leftarrow i}$ changes node $z$ to state $i$. The active boundary is $$\partial_{SI}(\omega)=\{(x,y)\in\overrightarrow E:\omega(x)=I,\ \omega(y)=S\}.$$ The total event rate is $(\lambda+\mu)|\partial_{SI}(\omega)|$, and an infection-versus-removal event has relative probabilities $\lambda/(\lambda+\mu)$ and $\mu/(\lambda+\mu)$. For neural use, let $h_i,s_i,r_i\geq0$ denote infected, susceptible, and removed masses with $h_i+s_i+r_i=1$. Define $$F_j=\lambda s_j\sum_iA_{ij}h_i,\qquad D_i=\mu h_i\sum_jA_{ij}s_j,$$ and update $$h_j^{t+1}=h_j^t+\Delta t F_j^t-\Delta t D_j^t,\quad r_j^{t+1}=r_j^t+\Delta t D_j^t,\quad s_j^{t+1}=1-h_j^{t+1}-r_j^{t+1}.$$ The key property is explicit competition: high susceptible degree increases both incoming propagation and removal of the source.

## Key formulas

- $$L_{\lambda,\mu}^{\mathrm{ZIM}}f(\omega)=\sum_{x:\omega(x)=I}\left(\mu\sum_{y:\omega(y)=S,\,x\sim y}[f(\omega^{x\leftarrow R})-f(\omega)]+\lambda\sum_{y:\omega(y)=S,\,x\sim y}[f(\omega^{y\leftarrow I})-f(\omega)]\right).$$
- $$\partial_{SI}(\omega)=\{(x,y)\in\overrightarrow E:\omega(x)=I,\ \omega(y)=S\}.$$
- $$\Pr(\mathrm{infection}\mid\omega)=\frac{\lambda}{\lambda+\mu},\qquad \Pr(\mathrm{removal}\mid\omega)=\frac{\mu}{\lambda+\mu}.$$
- $$F_j=\lambda s_j\sum_iA_{ij}h_i,\qquad D_i=\mu h_i\sum_jA_{ij}s_j,\qquad h_j^{t+1}=h_j^t+\Delta t(F_j-D_j).$$

## Implementation notes

Integrate this as an optional propagation block before the graph encoder's usual MLP or residual update. First compute node embeddings $x_i$ using a linear projection. Produce initial infected mass $h_i^0=\operatorname{sigmoid}(w_h^Tx_i)$, set $r_i^0=0$, and set $s_i^0=1-h_i^0$. For each of $K$ propagation steps, compute active edge mass $a_{ij}=A_{ij}h_i s_j$, incoming infection flux $F_j=\lambda\sum_i a_{ij}$, and source removal flux $D_i=\mu\sum_j a_{ij}$. Update `h = h + dt * (F - D)`, `r = r + dt * D`, and `s = 1 - h - r`; clamp all states to nonnegative values and renormalize each node's three states to sum to one. Use the accumulated flux to gate learned messages: `m_j = sum_t sum_i a_ij * Wv(x_i)`, followed by `x_out = x + MLP(m)`. Parameterize $\lambda$ and $\mu$ with softplus to keep them positive. The paper supplies the competing-event rates; the neural model learns the states and rates. Choose $\Delta t$ so that $\Delta t(\lambda+\mu)\max_i\deg(i)<0.25$. Start with a two-layer GCN or GraphSAGE on Cora, PubMed, and a synthetic tree task, matching parameter counts. Compare $K=2,4,8$ and $\mu/\lambda=0,0.1,0.3,1$. Success is higher accuracy on noisy or heterophilous graphs, lower cosine-similarity collapse across layers, and less degradation after adding irrelevant edges.

## Disclaimer

AI-generated research hypothesis, automatically tested. Not peer-reviewed.