Model-driven engineering (MDE) supports the engineering of complex systems via multiple models representing various systems' aspects. These interrelated models are usually heterogeneous and often specified using complementary modeling languages. Whenever needed, model view solutions can be employed to federate these models in a more transparent way. To do so, the required inter-model links can sometimes be automatically computed via explicitly written matching rules. However, in some cases, matching rules would be too complex (or even impossible) to write. Thus, some inter-model links may be inferred by analyzing previous examples instead. In this paper, we introduce a Machine Learning (ML)backed approach for expressing and computing such model views. Notably, we aim at making the use of ML as simple as possible in this context. To this end, we propose to refine and extend the ViewPoint Definition Language (VPDL) from the EMF Views model view solution to integrate the use of dedicated Heterogeneous Graph Neural Networks (HGNNs). These view-specific HGNNs can be trained with appropriate sets of contributing models before being used for inferring links to be added to the views.