Versions Compared

Key

  • This line was added.
  • This line was removed.
  • Formatting was changed.

https://www.lfedge.org/2021/10/21/akraino-r5-spotlight-on-the-ai-edge-federated-machine-learning-at-the-edge/ 

Enzo Zhang  zifan wu  haihui wang Ryan Anderson


By: Enzo Zhang  Zifan Wu  Haihui Wang, and Ryan Anderson

All attributes of each row data for Federated Machine Learning (ML) come from more than one data providers. They must be combined before  the whole information for Federated Machine Learning in AI Edge case. Each edge provider.  Each side has no ability on its own to hold all of  data required. Edge side has much pretty limitation for edge computing because of variety of conditions.of the required data to function as designed. Specific edges (or edge sides) can be pretty limited in terms of edge computing capabilities for a variety of reasons/conditions

The application must cover edges more than one and collect and exchange edge while also collecting and exchanging data between edges. Meanwhile, a method must be applied to make sure the communication between these edges is secure enough for all participants.

See Here are some examples of  AI edge application case as following.use cases to illustrate:  

  • Deploy more than one edge
  • No more extra storage space
  • A few computing units
  • Deal with data locally
  • Network ability
  • Share data each othersother
  • Work together with ML
  • Data security

Image ModifiedImage Modified

Application groups Applications group data from edges base security method, Data based on security methods; but data privacy is still going to managed by the Federated Machine Learning framework.  Data, as an  input of machine learning model was a ML model,  is in a central site, data exchange was placed after machine learning and  exchange of data occurs after ML processes are done.  Model with required data was send Required data gets sent back to the edge for its next process.

Many key components are required to make the case works work well and machine learning run successsuccessfully:.

  1. Data transfer and group
  2. Data collect and distribute
  3. Federated Machine Learning framework
  4. Security encryption algorithm

Functionality This functionality, integrated with the framework make edge application run in right way and keep data security., can enable edge applications to run right correctly and securely.