Non-intrusive load monitoring (NILM) can monitor the operating state and energy consumption of electric appliances in a non-intrusive manner and provides a promising approach to improving electricity usage efficiency for residential and commercial buildings. Although machine learning (ML) methods are powerful and have significantly advanced the developments of NILM, they request a sizable amount of labelled data for model training. However, getting operational data of each elec- trical appliance in real life is challenging, so the requirements for labelled data limit the NLIM's practicality. To tackle this challenge, a novel multi-layer momentum contrast (MLMoCo) learning mechanism is proposed for self-supervised feature rep- resentation learning. With only unlabelled aggregate load data, the proposed MLMoCo contrasts the augmented versions of the same sample (“positives”) with instances extracted from other samples (“negatives”). To maintain a dictionary with enough negative samples to be compared with the input, a momentum encoder is adopted to momentum update the parameters rather than by backpropagation during training. An event-based data augmentation method is also proposed to obtain the distinct but strongly related positive pairs for self-supervised feature learning. The experimental comparisons, including different state-of-the- art techniques and various downstream tasks with real-world datasets, demonstrate the remarkable performance gains of the proposed approach through learning from the unlabelled data, which could significantly increase the practicality of the NILM.