# US 2025/0148352 A1 · Explainable federated learning robust to malicious clients and to non-independent and identically distributed data

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2025/0148352 A1
- Document ID: US20250148352A1
- Status: Published application
- Kind: A1
- Application number: 18/501,784
- Filed: 2023-11-03
- Published: 2025-05-08
- Earliest claimed: 2023-11-03
- Assignees: Dell Products L.P.
- Applicants: Dell Products L.P.
- Inventors: Jonathan Mendes De Almeida; Eduarda Tatiane Caetano Chagas; Paulo Abelha Ferreira
- Web page: https://patentgrep.com/patent/US20250148352A1

## CPC

- G06N 20/00: Machine learning
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS

## Abstract

Techniques are disclosed for explainable federated learning. An example method includes receiving, at a central node, relative importances for a plurality of features input into a machine learning (ML) model usable at an edge node, thereby defining a plurality of feature importances, the central node being configured to communicate with the edge nodes; using, at the central node, an ML algorithm to classify the edge nodes into a number ‘k’ of node groups based on the feature importances; and for each node group among the ‘k’ node groups: generating, at the central node, an ML shared model using the feature importances associated with a selected subset of nodes in the node group; and deploying, at the central node, the shared model to each edge node in the node group.

## Claims

### Claim 1

A system comprising:
at least one processing device including a processor coupled to a memory;
the at least one processing device being configured to implement the following steps:
receiving, at a central node, relative importances for a plurality of features input into a machine learning (ML) model usable at an edge node, thereby defining a plurality of feature importances, the central node being configured to communicate with the edge nodes;
using, at the central node, an ML algorithm to classify the edge nodes into a number ‘k’ of node groups based on the feature importances; and
for each node group among the ‘k’ node groups:
generating, at the central node, an ML shared model using the feature importances associated with a selected subset of nodes in the node group; and
deploying, at the central node, the shared model to each edge node in the node group.

### Claim 2 (depends on 1)

The system of claim 1, wherein the feature importances are determined using in-training feature extraction.

### Claim 3 (depends on 2)

The system of claim 2, wherein the in-training feature extraction is performed using header matrices.

### Claim 4 (depends on 1)

The system of claim 1,
wherein the feature importances are encrypted, and
wherein the at least one processing device is further configured to implement the following steps:
receiving, at the central node, model gradients.

### Claim 5 (depends on 4)

The system of claim 4, wherein the feature importances are encrypted using homomorphic encryption.

### Claim 6 (depends on 4)

The system of claim 4, wherein the feature importances are encrypted using secure aggregation.

### Claim 7 (depends on 1)

The system of claim 1, wherein the ML algorithm is k-means clustering.

### Claim 8 (depends on 7)

The system of claim 7, wherein the at least one processing device is further configured to implement the following steps:
determining the number ‘k’ of feature groups using an Elbow test.

### Claim 9 (depends on 7)

The system of claim 7, wherein the at least one processing device is further configured to implement the following steps:
determining the number ‘k’ of feature groups using a Silhouette test.

### Claim 10 (depends on 1)

The system of claim 1, wherein the subset of nodes is selected based on measuring a correlation between the feature importances for a given node and a set of feature importances for the node group.

### Claim 11 (depends on 10)

The system of claim 10, wherein the correlation is measured using a rank biased overlap test.

### Claim 12 (depends on 10)

The system of claim 10, wherein the correlation is measured using a Kendall Ranking Correlation Coefficient test.

### Claim 13

A method comprising:
receiving, at a central node, relative importances for a plurality of features input into a machine learning (ML) model usable at an edge node, thereby defining a plurality of feature importances, the central node being configured to communicate with the edge nodes;
using, at the central node, an ML algorithm to classify the edge nodes into a number ‘k’ of node groups based on the feature importances; and
for each node group among the ‘k’ node groups:
generating, at the central node, an ML shared model using the feature importances associated with a selected subset of nodes in the node group; and
deploying, at the central node, the shared model to each edge node in the node group.

### Claim 14 (depends on 13)

The method of claim 13, wherein the feature importances are determined using in-training feature extraction.

### Claim 15 (depends on 14)

The method of claim 14, wherein the in-training feature extraction is performed using header matrices.

### Claim 16 (depends on 13)

The method of claim 13,
wherein the feature importances are encrypted,
further comprising receiving, at the central node, model gradients.

### Claim 17 (depends on 16)

The method of claim 16, wherein the feature importances are encrypted using homomorphic encryption.

### Claim 18 (depends on 16)

The method of claim 16, wherein the feature importances are encrypted using secure aggregation.

### Claim 19 (depends on 13)

The method of claim 13, wherein the ML algorithm is k-means clustering.

### Claim 20

A non-transitory processor-readable storage medium having stored thereon program code of one or more software programs, wherein the program code when executed by at least one processing device causes the at least one processing device to perform the following steps:
receiving, at a central node, relative importances for a plurality of features input into a machine learning (ML) model usable at an edge node, thereby defining a plurality of feature importances, the central node being configured to communicate with the edge nodes;
using, at the central node, an ML algorithm to classify the edge nodes into a number ‘k’ of node groups based on the feature importances; and
for each node group among the ‘k’ node groups:
generating, at the central node, an ML shared model using the feature importances associated with a selected subset of nodes in the node group; and
deploying, at the central node, the shared model to each edge node in the node group.