Pre-Trained Model Adaptation with MPO Weight Updates

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Adapting large-scale pre-trained machine learning models to specific tasks requires significant computational resources and energy expenditure due to the large number of parameters, especially when training data is limited.

Innovation Solution

Utilizing quantum circuits to implement a matrix product operator (MPO) representation for task-specific parameter increments, which reduces the number of trainable parameters by constructing updates through a tensor network, and optionally leveraging variational quantum circuits to determine low-rank weight matrices for further parameter reduction.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If full fine-tuning is used to adapt pre-trained models to downstream tasks, then model accuracy for the specific task is improved, but computational cost and energy expenditure increase significantly

Engineering Contradiction:
Improvemodel accuracyVSAvoidcomputational cost
Core Design Contradiction:
Measurement precisionVSUse of energy by moving object

Solution Approach 1:

The patent extracts only the essential update information needed for task adaptation by representing weight updates as low-rank matrices. Instead of updating all parameters, the method extracts and trains only the low-rank update matrices ΔW that capture the necessary task-specific adjustments, significantly reducing computational cost while maintaining accuracy.

Inventive Principle:
Principle #2Taking out (Extraction)

Solution Approach 2:

The patent changes the parameter representation from full-rank weight matrices to low-rank factorized form. By expressing weight updates as products of low-rank matrices, the method transforms the optimization problem into one with fewer effective parameters, reducing computational complexity while preserving the essential information needed for task performance.

Inventive Principle:
Principle #35Parameter changes

2Adaptability or versatility

If conventional fine-tuning techniques are used with limited training data, then model adaptation is achieved, but accuracy is limited due to overfitting or insufficient learning

Engineering Contradiction:
Improvemodel adaptationVSAvoidaccuracy
Core Design Contradiction:
Adaptability or versatilityVSMeasurement precision

Solution Approach 1:

The patent changes the parameter representation to low-rank factorized form, which regularizes the optimization problem. This parameter transformation effectively reduces the search space and prevents overfitting when training data is limited, while still capturing task-specific patterns through the low-rank update matrices.

Inventive Principle:
Principle #35Parameter changes

3Reliability

If all model parameters are updated during adaptation, then complete model retraining is achieved, but training time increases significantly

Engineering Contradiction:
Improvemodel performanceVSAvoidtraining time
Core Design Contradiction:
ReliabilityVSLoss of time

Solution Approach 1:

The patent extracts only the essential update information needed for task adaptation by representing weight updates as low-rank matrices. Instead of updating all parameters, the method extracts and trains only the low-rank update matrices ΔW that capture the necessary task-specific adjustments, significantly reducing training time while maintaining accuracy.

Inventive Principle:
Principle #2Taking out (Extraction)

Solution Approach 2:

The patent applies partial action by updating only a subset of parameters (the low-rank update matrices) rather than all parameters. This partial parameter update approach is sufficient for task adaptation and avoids the time-consuming process of retraining the entire model.

Inventive Principle:
Principle #16Partial or excessive action

Data Source

PatentEP4685700A1Method and system for adapting a pre-trained machine learning model to a learning task
Publication Date: 2026.01.28 TERRA QUANTUM AG
  • EP4685700A1 patent drawingFigure 1
  • EP4685700A1 patent drawingFigure 2A~2C
  • EP4685700A1 patent drawingFigure 3

AI summary

A computer-implemented method for adapting a pre-trained machine learning model to a learning task, comprising receiving the pre-trained machine learning model comprising a plurality of learned weights for transforming an input towards an output, wherein the plurality of learned weights can be expressed with a weight matrix; performing a training process for adapting the pre-trained machine learning model to the learning task by updating a task-specific parameter increment added to the weight matrix, which is constructed from an MPO representation with a plurality of tensors each having an uncontracted first and second index, and a contracted index of a bond dimension, wherein a product of dimensions of the uncontracted first and second indices of the tensors are at least equal to a first dimension and a second dimension of the weight matrix, respectively, and wherein entries of the tensors are trainable parameters of the training process.