# US 2026/0228555 A1 · Methods and systems for distance based sequencing in continual learning

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

- Number: US 2026/0228555 A1
- Document ID: US20260228555A1
- Status: Published application
- Kind: A1
- Application number: 19/043,058
- Filed: 2025-01-31
- Published: 2026-08-06
- Earliest claimed: 2025-01-31
- Applicants: Huawei Technologies Co., Ltd.
- Inventors: Hesham Gamal Aly Mohammed MOUSSA
- Web page: https://patentgrep.com/patent/US20260228555A1

## CPC

- G06N 3/045: Combinations of networks
- G06N 3/096: Transfer learning
- G06N 3/006: based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
- G06N 3/04: Architecture, e.g. interconnection topology
- G06N 3/044: Recurrent networks, e.g. Hopfield networks
- G06N 3/0464: Convolutional networks [CNN, ConvNet]
- G06N 3/047: Probabilistic or stochastic networks
- G06N 3/048: Activation functions
- G06N 3/063: using electronic means
- G06N 3/08: Learning methods
- G06N 3/082: modifying the architecture, e.g. adding, deleting or silencing nodes or connections
- G06N 3/084: Backpropagation, e.g. using gradient descent
- G06N 3/088: Non-supervised learning, e.g. competitive learning
- G06N 3/09: Supervised learning
- G06N 3/098: Distributed learning, e.g. federated learning
- G06N 5/01: Dynamic search techniques; Heuristics; Dynamic trees; Branch-and-bound
- G06N 5/022: Knowledge engineering; Knowledge acquisition
- G06N 5/043: Distributed expert systems; Blackboards
- G06N 20/00: Machine learning
- G06N 20/20: Ensemble learning
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS

## Abstract

Method and systems for training an AI model on datasets from a plurality of nodes connected to form a knowledge sharing network. The method comprises identifying a first host node in the knowledge sharing network that is currently hosting the AI model to train the model according to a first data set associated with the first host node; determining a comparative distance measure between the first dataset associated with the first host node and each dataset associated with each node in the knowledge sharing network; identifying the next host node in the knowledge sharing network based on a decision rule that evaluates the comparative distance measures from each of the nodes available for hosting; moving the AI model trained on the first host node towards the identified next host node to continue training the AI model according to a dataset associated with the identified next host node.

## Claims

### Claim 1

A method of training a model on datasets from a plurality of nodes in a network, the method performed by one or more computer processors executing software instructions, the method comprising:
identifying a first host node in the network that is currently hosting the model to train the model according to a first data set associated with the first node;
determining a comparative distance measure from each node in the network that is available for hosting training to becoming a next host node; and
identifying the next host node in the network based on a decision rule that evaluates the comparative distance measure for each available node.

### Claim 2 (depends on 1)

The method of claim 1, wherein the comparative distance measure comprises a Fisher distance.

### Claim 3 (depends on 2)

The method of claim 2, further comprising sending a trigger for available nodes to indicate a state to be considered as the next host node.

### Claim 4 (depends on 3)

The method of claim 3, further requesting each available node configured to provide a Fisher distance based on a Fisher information matrix (FIM).

### Claim 5 (depends on 4)

The method of claim 4, wherein the Fisher distance is calculated based on the following equation:
D
θ
t
=
{
d
θ
t
[
i
,
j
]
}
i
≠
j
,
∀
j
∈
(
1
,
2
,
…
,
N
)
where: Dθt is a vector containing a set of fisher distances between the ith dataset and the jth dataset with respect to model weights at time t given by θt θt corresponds to the model weights after training on the dataset associated with the current host node.

### Claim 6 (depends on 2)

The method of claim 2, wherein the decision rule is based on the Fisher Distance.

### Claim 7 (depends on 2)

The method of claim 2, wherein the decision rule is based on comparing the Fisher Distance with a target value indicative of a model parameter.

### Claim 8 (depends on 1)

The method of claim 1, wherein the decision rule selects as the next node a node with one of: a furthest distance from the first host node or a closest distance to the first host node.

### Claim 9 (depends on 1)

The method of claim 1, comprising one of the plurality of nodes acting as a computing surrogate node for another one of the plurality of nodes, the computing surrogate node receiving a minibatch of data from the dataset of the another node and determining the comparative distance measure on behalf of the another node using the model based on the minibatch.

### Claim 10 (depends on 1)

The method of claim 1, comprising a central sequencer receiving the model from the host node and a minibatch of data from the dataset of each of the plurality of nodes and determining the comparative distance measure for each of the nodes using the model based on the minibatch.

### Claim 11 (depends on 1)

The method of claim 1, comprising a central sequencer receiving the comparative distance measure determined at each of the nodes, the central sequencer identifying the next host node based on the received comparative distance measures.

### Claim 12 (depends on 1)

The method of claim 1, wherein the comparative distance measure is determined using the model and a minibatch or sample of the dataset of each of the nodes.

### Claim 13 (depends on 1)

The method of claim 1, wherein the comparative distance measure represents a distance in parameter space between the model as trained by the dataset of the host node and the model as trained by a sample of the dataset of each of the plurality of nodes.

### Claim 14 (depends on 1)

The method of claim 1, wherein the network is one or more of: decentralized, centralized, fully connected and hierarchical.

### Claim 15 (depends on 1)

The method of claim 1, wherein the model comprises a neural network.

### Claim 16 (depends on 1)

The method of claim 1, wherein the network comprises multiple networks each comprising one or more nodes to be trained.

### Claim 17 (depends on 1)

The method of claim 1, wherein the network comprises multiple networks, each of the multiple networks comprising a cluster of nodes, wherein the comparative distance measure is communicated from a designated head node of each of the clusters of nodes without communicating the datasets or a part thereof between the clusters of nodes.

### Claim 18

A method of training an Artificial Intelligence (AI) model on datasets from a plurality of nodes connected to form a knowledge sharing network, the method performed by at least one computer processor executing programming instructions, the method comprising:
identifying a first host node in the knowledge sharing network that is currently hosting the AI model to train the model according to a first data set associated with the first host node;
determining a comparative distance measure between the first dataset associated with the first host node and each dataset associated with each node in the knowledge sharing network that is available for hosting and continue training the AI model to becoming a next host node;
identifying the next host node in the knowledge sharing network based on a decision rule that evaluates the comparative distance measures from each of the nodes available for hosting;
moving the AI model trained on the first host node towards the identified next host node to continue training the AI model according to a dataset associated with the identified next host node; and
stopping the next host node identification based on a set of predefined stoppage criteria.

### Claim 19 (depends on 18)

The method of claim 18, wherein the stoppage criteria comprises at least one of a training target performance metric being achieved and the nodes available for hosting being exhausted.

### Claim 20

A computer program product comprising instructions which, when the program is executed by a computer, cause the computer to carry out the steps of
identifying a first host node in a network that is currently hosting a model to train the model according to a first data set associated with the first node;
determining a comparative distance measure from each node in the network that is available for hosting training to becoming a next host node
identifying the next host node in the network based on a decision rule that evaluates the comparative distance measures for each node that is available for hosting training.
