Go To MPAI-OSD AI Modules

1 Function 2 Reference Model 3 Input/Output Data
4 SubAIMs 5 JSON Metadata 6 Profiles
7 Reference Software 8 Conformance Texting 9 Performance Assessment

1 Functions

The Health Federated Learning (AIH-HFL) AIM:

Receives NN Model Requested to and obtained from HFEs
Assembles NN Models Received from HFEs
Produces FL Request To request NN Models to HFEs.
NN Model New NN Model uploaded to MPAI Store.

2 Reference Model

The Health Federated Learning (AIH-HFL) AIM Reference Model is depicted in Figure 1.

Figure 1 – The Health Federated Learning (AIH-HFL) AIM Reference Model

3 Input/Output Data

Table 1 specifies the Input and Output Data of the Health Federated Learning (AIH-HFL) AIM. Links are to the Data Type specifications.

Table 1 – I/O Data of the Health Federated Learning (AIH-HFL) AIM

Input Description
NN Model From HFEs
Output Description
NN Model Request To HFEs
NN Model New NN Model uploaded to MPAI Store.

4 SubAIMs

No SubAIMs

5 JSON Metadata

https://schemas.mpai.community/AIH1/V1.0/AIMs/HealthFederatedLearning.json

6 Profiles

No Profiles

7 Reference Software

Under development.

8 Conformance Testing

Table 2 provides the Conformance Testing Method for the Health Federated Learning (AIH-HFL) AIM.

If a schema contains references to other schemas, conformance of data for the primary schema implies that any data referencing a secondary schema shall also validate against the relevant schema, if present and conform with the Qualifier, if present.

Table 2 – Conformance Testing Method for Health Federated Learning (AIH-HFL) AIM

Receives NN Model Shall validate against Machine Learning Model schema.
Produces NN Request Shall validate against NN Request schema.
NN Model Shall validate against  Machine Learning Model schema.

9 Performance Assessment

Go To MPAI-OSD AI Modules