The topic of indoor localization is very relevant today as it provides solutions in different applications (e.g. shopping malls or museums). We consider here the so-called Wi-Fi fingerprinting approach, where RSSI measurements from the access points are used to locate the device into certain predefined areas. Typically, this mapping from measurements to area is obtained by training a machine learning algorithm. However, traditional techniques do not take into account the underlying geometry of the problem. We thus investigate here a novel approach : using machine learning techniques in graphs, in particular Graph Neural Networks. We propose a way to construct the graph using only the RSSI measurements (and not the floor plan) and evaluate the resulting algorithm on two real datasets. The results are very encouraging, showing a better performance than existing methods, in some cases even using a much smaller amount of training data.