Introduction#

What is vantage6?#

Vantage6 stands for privacy preserving federated learning infrastructure for secure insight exchange.

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.

What vantage6 does:

  • 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

What vantage6 does not (yet) do:

  • formatting the data at the data station

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

The vantage6 infrastructure 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.

Overview of this documentation#

This documentation space consists of the following main sections:

  • IntroductionYou are here now

  • User guideHow to use vantage6 as a researcher

  • Node admin guideHow to install and configure vantage6 nodes

  • Server admin guideHow to configure and deploy vantage6 servers

  • Technical Docs (Under construction) → Implementation details of the vantage6 platform

  • Developer communityHow to collaborate on the development of the vantage6 infrastructure

  • Algorithm DevelopmentDevelop algorithms that are compatible with vantage6

  • GlossaryA dictionary of common terms used in these docs

  • Release notesLog of what has been released and when

Vantage6 resources#

This is a - non-exhaustive - list of vantage6 resources.

Documentation

Source code

  • vantage6Contains all components (and the python-client).

  • PlanningContains all features, bugfixes and feature requests we are working on. To submit one yourself, you can create a new issue.

Community


Index#