Rotational Equivariance Improves Neural Routing Solvers

Although rotational-equivariant neural networks have proven to be an effective architectural bias across domains from chemistry to robotics, such approaches remain largely under-explored in the design of neural solvers for combinatorial optimization. In this work, we focus on Euclidean routing problems—specifically, the traveling salesman problem and the capacitated vehicle routing problem. For these problems, we experimentally demonstrate that converting existing neural solvers into their rotational-equivariant versions can boost their performance and generalization capabilities.