Fig. 2
Network inference overview. Step 1: The top five models in the training dataset most similar to the input model (based on model feature similarity) were identified. The target nodes directly connected to these models were then designated as primary nodes, serving as the starting points for network inference. Step 2: Using the trained GNN model, all candidate paths were explored from the primary nodes (start nodes) toward the input target nodes, which served as the goal nodes. Step 3: For each source–target node pair along the paths, the optimal edge was selected from a pool of candidate edges. The edge selection criterion required that the source node of the current edge closely matched the target node of the previous edge in the sequence (i.e., en-1[tgt] ≈ en[src]), thereby ensuring topological continuity toward the goal node. Step 4: Message passing was applied along each candidate path. For the first target node, the attention weight (attn_W) from the connected model node was applied. Subsequent nodes received propagated signals scaled by the sigmoid-transformed Euclidean norm of the previous node’s feature (i.e., σ(║xn║2)). The predicted feature of each goal node (xgoal) was obtained at the end of the path. The best combination of paths was selected for each goal node by minimizing the Euclidean distance between the predicted node feature and the actual input feature across all possible path combinations.
