Efficient Meta Neural Heuristic for Multi-Objective Combinatorial Optimization (Appendix) A Model architecture The architecture of the base model in meta-learning is the same as POMO [ 26

Each sublayer adds a skip-connection (ADD) and batch normalization (BN). The decoder sequentially chooses a node according to a probability distribution produced by the node embeddings to construct a solution. The scaled symmetric sampling method is shown in Algorithm 2. The scaled factor The uniform division of the weight space is illustrated as follows. Thus, its approximate Pareto optimal solutions are commonly pursued. V ehicles must serve all the customers and finally return to the depot.