The connectional brain template (CBT) is a compact representation (i.e., a single connectivity matrix) multi-view brain networks of a given population. CBTs are especially very powerful tools in brain dysconnectivity diagnosis as well as holistic brain mapping if they are learned properly – i.e., occupy the center of the given population. Even though accessing large-scale datasets is much easier nowadays, it is still challenging to upload all these clinical datasets in a server altogether due to the data privacy and sensitivity. Federated learning, on the other hand, has opened a new era for machine learning algorithms where different computers are trained together via a distributed system. Each computer (i.e., a client) connected to a server, trains a model with its local dataset and sends its learnt model weights back to the server. Then, the server aggregates these weights thereby outputting global model weights encapsulating information drawn from different datasets in a privacy-preserving manner. Such a pipeline endows the global model with a generalizability power as it implicitly benefits from the diversity of the local datasets. In this work, we propose the first federated connectional brain template learning (Fed-CBT) framework to learn how to integrate multi-view brain connectomic datasets collected by different hospitals into a single representative connectivity map. First, we choose a random fraction of hospitals to train our global model. Next, all hospitals send their model weights to the server to aggregate them. We also introduce a weighting method for aggregating model weights to take full benefit from all hospitals. Our model to the best of our knowledge is the first and only federated pipeline to estimate connectional brain templates using graph neural networks. Our Fed-CBT code is available at https://github.com/basiralab/Fed-CBT.