This section will describe the community, the overall architecture of the platform and explains how this documentation space is organized.


This documentation space consists of 7 main sections:

  • IntroductionYou are here now
  • User DocsInstall and use vantage6-servers, -nodes or -clients
  • Technical Docs → Implementation details of the vantage6 platform*
  • Dev communityHow to collaborate on the development of the vantage6 infrastructure
  • Algorithm DevDevelop algorithms that are compatible with vantage6
  • Release notes → changelog to the source code
  • Glossary



Source code

  • vantage6contains all components (and the python-client).
  • Planning → contains all features, bugfixes and feature request we are working on. To submit one yourself, you can create a new issue.


What is vantage6?

Vantage6 stands for privacy preserving federated learninginfrastructure for secure insight exchange. A more technical explanation would be: a container orchastration tool for privacy preserving analysis. Watch this video for a quick introduction.

The project is inspired by the Personal Health Train (PHT) concept. In this analogy vantage6 is the tracks and stations. Compatible algorithms are the trains, and computation tasks are the journey. Vantage6 is completely open source under the Apache License.

vantage6 is here for:

  • delivering algorithms to data stations and collecting their results
  • managing users, organizations, collaborations, computation tasks and their results
  • providing control (security) at the data-stations to their owners

vantage6 is not (yet):

  • formatting the data at the data station
  • aligning data across the data stations (for the vertical partitioned use case)

vantage6 is designed with three fundamental functional aspects of Federated learning.

  1. Autonomy. All involved parties should remain independent and autonomous.
  2. Heterogeneity. Parties should be allowed to have differences in hardware and operating systems.
  3. Flexibility. Related to the latter, a federated learning infrastructure should not limit the use of relevant data.


Vantage6 uses both a client-server and peer-to-peer model. In the figure below the client can pose a question to the server, the question is then delivered as an algorithm to the node. When the algorithm completes, the results are sent back to the client via the server. An algorithm can communicate directly with other algorithms that run on other nodes if required.

Architecture overview

Fig. 1 Vantage6 has a client server architecture. (A) The Client is used by the researcher to create computation requests. It is also used to manage users, organizations and collaborations. (B) The Server contains users, organizations, collaborations, tasks and their results. (C) The Node has access to data and handles computation requests from the server.

The server is in charge of processing the tasks as well as of handling administrative functions such as authentication and authorization. Conceptually, vantage6 consists of the following parts:

  • A (central) server that coordinates communication with clients and nodes
  • One or more node(s) that have access to data and execute algorithms
  • Organizations that are interested in collaborating;
  • Users (i.e. researchers or other applications) that request computations from the nodes
  • A Docker registry that functions as database of algorithms