In this paper we consider the problem of decentralized (distributed) adaptive learning, where the aim of the network is to train the coefficients of a widely linear autoregressive moving average (ARMA) model by measurements collected by the nodes. Such a problem arises in many sensor network-based applications such as target tracking, fast rerouting, data reduction and data aggregation. We assume that each node of the network uses the augmented complex adaptive infinite impulse response (ACAIIR) filter as the learning rule, and nodes interact with each other under an incremental mode of cooperation. Since the proposed algorithm (incremental augmented complex IIR (IACA-IIR) algorithm) relies on the augmented complex statistics, it can be used to model both types of complex-valued signals (proper and improper signals). To evaluate the performance of the proposed algorithm, we use both synthetic and real-world complex signals in our simulations. The results exhibit superior performance of the proposed algorithm over the non-cooperative ACAIIR algorithm.