Learning Combinatorial Node Labeling Algorithms. (arXiv:2106.03594v3 [cs.LG] UPDATED)

We present a novel neural architecture to solve graph optimization problems
where the solution consists of arbitrary node labels, allowing us to solve hard
problems like graph coloring. We train our model using reinforcement learning,
specifically policy gradients, which gives us both a greedy and a probabilistic
policy. Our architecture builds on a graph attention network and uses several
inductive biases to improve solution quality. Our learned deterministic
heuristics for graph coloring give better solutions than classical degree-based
greedy heuristics …

algorithms arxiv labeling learning node