Abstract We consider a multi-operator small cell network where mobile network operators are sharing a common pool of radio resources. The goal is to ensure long term fairness of spectrum sharing without coordination among small cell base stations. It is assumed that spectral allocation of the small cells is orthogonal to the macro network layer, and thus, only the small cell traffic is modeled. We develop a decentralized control mechanism for base stations using the Gibbs sampling based learning technique, which allocates a suitable amount of spectrum for each base station. Five algorithms are compared addressing co-primary multi-operator resource sharing under heterogeneous traffic requirements and the performance is assessed through extensive system-level simulations. The main performance metrics are user throughput and fairness between operators. The numerical results demonstrate that the proposed Gibbs sampling based learning algorithm provides about tenfold cell edge throughput gains compared to state-of-the-art algorithms, while ensuring fairness between operators.