Difference between revisions of "Federated Learning"

From MgmtWiki
Jump to: navigation, search
(Context)
(Privacy Enhancing)
Line 12: Line 12:
 
==Privacy Enhancing==
 
==Privacy Enhancing==
 
To make the graph privacy-enhancing we demand that any personally identifiable information (PII) is restricted to the leaves.
 
To make the graph privacy-enhancing we demand that any personally identifiable information (PII) is restricted to the leaves.
 +
 +
==Using Test Data==
 +
The goal is to determine whether selecting data in a manner that mirrors real life and federating populations that mirror real life will be cost to the results with uniform sorting.
 +
# Break the population into two groups that are randomly selected from the populations and getting a result with a single aggregation of those two sets.
 +
# Break the population into 50 groups with random selection.
 +
# Break the population into 50 groups with deliberately selected groups be overrepresented in each group.
 +
# Aggregate each selection into a single distribution.
 +
# Measure the discrepancy between the results.
  
 
==References==
 
==References==
  
 
[[Category: Artificial Intelligence]]
 
[[Category: Artificial Intelligence]]

Revision as of 18:08, 2 September 2022

Full Title

A means of learning where the nodes can operate independently to create a common understanding of a problem.


Context

  • Most human learning is federated in the sense that each human operates as an independent entity which receives inputs and creates outputs.
  • In this pattern we model the human tendency to spread processing to each node with a similar hierarchy of capability among the nodes.

A Hierarchical Directed Graph

One solution is to create a network of all nodes that run any learning algorithm into a tree with paths that always move towards the root and away from the leaves as well as paths that go from the root out to the leaves.

Privacy Enhancing

To make the graph privacy-enhancing we demand that any personally identifiable information (PII) is restricted to the leaves.

Using Test Data

The goal is to determine whether selecting data in a manner that mirrors real life and federating populations that mirror real life will be cost to the results with uniform sorting.

  1. Break the population into two groups that are randomly selected from the populations and getting a result with a single aggregation of those two sets.
  2. Break the population into 50 groups with random selection.
  3. Break the population into 50 groups with deliberately selected groups be overrepresented in each group.
  4. Aggregate each selection into a single distribution.
  5. Measure the discrepancy between the results.

References