Difference between revisions of "Federated Learning"

Revision as of 07:46, 3 September 2022

Full Title

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

==Goals--

1. Accuracy in predicting when a pandemic is likely to occur. But false positives are less problematic than false negatives.
2. Universality - in predicting all types of pandemic
3. Reproductivity - in the face of growing skepticism in the results of AI.^[1]
4. Adaptability - in the face of constant advances in knowledge of AI.

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 meaning that it never is processed anywhere but within the medical facility where it is already maintained with full personal data. Only the learning from the data is passed up to the aggregator.
• The question to be determine is where this privacy guarantee will adversely impact the accuracy of the learning process.

Using Test Data

• Test data will not likely be distributed as it would be in real life.
• The goal is to determine whether selecting data in a manner that mirrors real life and federating populations that mirror real life will be lost to the results with uniform sorting. The following plan is designed to show the impact of distributing data the way that data is likely to be separated in the real world.

1. Break the synthetic data into two groups that are randomly selected from the data 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 and of widely different numbers of individuals.
4. Aggregate each selection into a single distribution.
5. Measure the discrepancy between the results to see impact of real-world distributions on the federated learning.

References

1. ↑ Will Knight, Sloppy Use of Machine Learning Is Causing a ‘Reproducibility Crisis’ in Science Wired 2022-08-10 https://www.wired.com/story/machine-learning-reproducibility-crisis/