Learning object-centric representations of complex scenes is a promising step towards enabling efficient abstract reasoning from low-levelperceptual features. Yet, most deep learning approaches learn distributed representations that do not capture the compositional properties of natural scenes.

Community detection is an essential tool for unsupervised data exploration and revealing theorganisational structure ofnetworkedsystems. Withalong history innetwork science, community detection typically relies on objectivefunctions, optimised with custom-tailored search algorithms, but often without leveraging recentadvancesindeeplearning.

However, they left the adapting to unknown ε as an open question.