In this paper, the problem of adaptive decentralized proportional-integral (PI) tracking control is investigated for a class of interconnected nonlinear systems with input quantization and unknown functions, where the interconnection terms are bounded by completely unknown functions. By designing an input-driven filter, the unknown states are estimated and then an adaptive decentralized output feedback PI tracking controller is constructed via the backstepping method and neural network technique. The stability of the closed-loop system is addressed based on the Lyapunov function technique plus graph theory, and all the signals in the closed-loop system are uniformly ultimately bounded. Finally, simulation results are utilized to demonstrate the effectiveness of the proposed method.