# US 2026/0087412 A1 · Meta-learning with diverse tasks

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

- Number: US 2026/0087412 A1
- Document ID: US20260087412A1
- Status: Published application
- Kind: A1
- Application number: 19/333,072
- Filed: 2025-09-18
- Published: 2026-03-26
- Earliest claimed: 2024-09-23
- Assignees: The Toronto-Dominion Bank
- Applicants: The Toronto-Dominion Bank
- Inventors: Jesse Cole Cresswell; Yi Sui; Keyvan Golestan Irani; Maksims Volkovs; Wei Cui
- Web page: https://patentgrep.com/patent/US20260087412A1

## CPC

- G06N 5/04: Inference or reasoning models
- G06N 20/00: Machine learning
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS

## Abstract

Meta-learning models are improved for few-shot learning of unseen tasks by improving task diversity of training data used for training the meta-learning model. A task diversity score may be determined between a pair of tasks that partition a domain into respective classes. The respective classes are paired and scored to determine similarity between class pairs and subsequent task diversity scores. Diverse tasks may be generated with unsupervised analysis of the domain by determining disentangled latent features of the data samples. Each latent feature may then be considered a task with classes based on a clustering of the data samples based on the feature values of the respective latent feature. The classes are then used as training task labels for the data samples and sampled from to generate diverse tasks for the meta-learning model.

## Claims

### Claim 1

A system for improving meta-learning model performance, comprising:
one or more processors configured to execute instructions; and
one or more computer-readable media containing instructions executable by the processors for:
identifying a first task partition of data samples of a domain with a first set of classes and a second task partition of data samples of the domain with a second set of classes;
determining a plurality of class pairs between the first set of classes and the second set of classes based on data samples in common between the class pairs;
determining a plurality of similarity scores, each similarity score corresponding to a class pair in the plurality of class pairs;
determining a task diversity score for the first task partition relative to the second task partition based on the plurality of similarity scores; and
determining, based on the task diversity score, a set of training data tasks for a meta-learning model for the domain.

### Claim 2 (depends on 1)

The system of claim 1, wherein the instructions are further executable for training the meta-learning model based on the set of training data tasks.

### Claim 3 (depends on 1)

The system of claim 1, wherein the similarity score is an intersection over union of data samples associated with the pair of classes.

### Claim 4 (depends on 1)

The system of claim 1, wherein determining the task diversity score includes averages of the plurality of similarity scores.

### Claim 5 (depends on 1)

The system of claim 1, wherein the plurality of class pairs is determined to increase the similarity scores of the plurality of class pairs.

### Claim 6 (depends on 1)

The system of claim 1, wherein the plurality of class pairs is a bipartite matching of the first set of classes and the second set of classes.

### Claim 7 (depends on 1)

The system of claim 1, wherein the second task partition is associated with an additional task to be added to the set of training data tasks; and
determining the set of training data tasks comprises adding the additional task to the set of training data tasks when the task diversity score is above a threshold.

### Claim 8 (depends on 1)

The system of claim 1, wherein the first task partition and the second task partition are determined by a first task generation algorithm, and wherein the instructions are further executable for:
determining another task diversity score for a third task partition and a fourth task partition determined by a second task generation algorithm; and
determining the set of training data tasks comprises including tasks from the first task generation algorithm in the set of training data tasks based on a comparison of the task diversity score with the other task diversity score.

### Claim 9

A computer-implemented method for improving meta-learning model performance, comprising:
identifying a first task partition of data samples of a domain with a first set of classes and a second task partition of data samples of the domain with a second set of classes;
determining a plurality of class pairs between the first set of classes and the second set of classes based on data samples in common between the class pairs;
determining a plurality of similarity scores, each similarity score corresponding to a class pair in the plurality of class pairs;
determining a task diversity score for the first task partition relative to the second task partition based on the plurality of similarity scores; and
determining, based on the task diversity score, a set of training data tasks for a meta-learning model for the domain.

### Claim 10 (depends on 9)

The method of claim 9, further comprising training the meta-learning model based on the set of training data tasks.

### Claim 11 (depends on 9)

The method of claim 9, wherein the similarity score is an intersection over union of data samples associated with the pair of classes.

### Claim 12 (depends on 9)

The method of claim 9, wherein determining the task diversity score includes averages of the plurality of similarity scores.

### Claim 13 (depends on 9)

The method of claim 9, wherein the plurality of class pairs is determined to increase the similarity scores of the plurality of class pairs.

### Claim 14 (depends on 9)

The method of claim 9, wherein the plurality of class pairs is a bipartite matching of the first set of classes and the second set of classes.

### Claim 15 (depends on 9)

The method of claim 9, wherein the second task partition is associated with an additional task to be added to the set of training data tasks; and
the method for determining the set of training data tasks comprises adding the additional task to the set of training data tasks when the task diversity score is above a threshold.

### Claim 16 (depends on 9)

The method of claim 9, wherein the first task partition and the second task partition are determined by a first task generation algorithm, and wherein the method further comprises:
determining another task diversity score for a third task partition and a fourth task partition determined by a second task generation algorithm; and
the method for determining the set of training data tasks comprises including tasks from the first task generation algorithm in the set of training data tasks based on a comparison of the task diversity score with the other task diversity score.

### Claim 17

A non-transitory computer-readable medium for improving meta-learning model performance, the non-transitory computer-readable medium comprising instructions executable by a processor for:
identifying a first task partition of data samples of a domain with a first set of classes and a second task partition of data samples of the domain with a second set of classes;
determining a plurality of class pairs between the first set of classes and the second set of classes based on data samples in common between the class pairs;
determining a plurality of similarity scores, each similarity score corresponding to a class pair in the plurality of class pairs;
determining a task diversity score for the first task partition relative to the second task partition based on the plurality of similarity scores; and
determining, based on the task diversity score, a set of training data tasks for a meta-learning model for the domain.

### Claim 18 (depends on 17)

The non-transitory computer-readable medium of claim 17, wherein the instructions are further executable by the processor for comprising training the meta-learning model based on the set of training data tasks.

### Claim 19 (depends on 17)

The non-transitory computer-readable medium of claim 17, wherein the similarity score is an intersection over union of data samples associated with the pair of classes.

### Claim 20 (depends on 17)

The non-transitory computer-readable medium of claim 17, wherein determining the task diversity score includes averages of the plurality of similarity scores.
