Transformer Attention Head Adaptation for New Task Transfer

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Transformer-based machine learning models, particularly visual-language models, suffer from image understanding errors when adapting to new domains, leading to performance degradation due to reliance on pre-trained and frozen visual encoders.

Innovation Solution

Adapt transformer-based models by selectively updating only the parameters of relevant attention heads using a loss function and applying low-rank updates, while freezing other parameters, to maintain knowledge from pre-training and improve performance on new tasks.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Stability of the object's composition

If the visual encoder is pre-trained and frozen to maintain stability, then the model structure remains stable and pre-trained knowledge is preserved, but the model cannot adapt to new domains and exhibits image understanding errors

Engineering Contradiction:
Improvemodel stabilityVSAvoiddomain adaptability
Core Design Contradiction:
Stability of the object's compositionVSAdaptability or versatility

Solution Approach 1:

The model parameters are segmented into two distinct groups: frozen pre-trained parameters and trainable adaptation parameters. This segmentation allows the stable pre-trained visual encoder to maintain its knowledge while specific parameter subsets can be adapted to new domains through selective training, resolving the contradiction between stability and adaptability.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

Instead of uniformly freezing or training all parameters, the invention applies different treatment to different parameter locations. Pre-trained parameters remain frozen to preserve stability, while specifically selected parameters (such as those in adapter modules or certain transformer layers) are made trainable to enable domain adaptation, implementing local quality differentiation.

Inventive Principle:
Principle #3Local quality

2Adaptability or versatility

If all model parameters are updated to adapt to a new task, then the model achieves better performance on the new task, but knowledge from pre-training is lost

Engineering Contradiction:
Improvetask adaptabilityVSAvoidpre-trained knowledge
Core Design Contradiction:
Adaptability or versatilityVSLoss of information

Solution Approach 1:

The invention extracts and isolates only the necessary parameters for task adaptation while leaving the majority of pre-trained parameters frozen. By taking out only the essential adaptable parameters for training, the model achieves task adaptability without losing the bulk of pre-trained knowledge, directly addressing the contradiction between adaptation and knowledge retention.

Inventive Principle:
Principle #2Taking out (Extraction)

Solution Approach 2:

The invention selectively changes parameters rather than uniformly updating all parameters. By identifying and modifying only specific parameter subsets that are critical for new task performance while keeping other parameters fixed, the model adapts to new tasks effectively while preserving pre-trained knowledge, resolving the contradiction between adaptability and knowledge retention.

Inventive Principle:
Principle #35Parameter changes

3Reliability

If the entire model is fine-tuned for a new task, then the model achieves optimal performance, but the computational requirements and training time increase significantly

Engineering Contradiction:
Improvemodel performanceVSAvoidtraining efficiency
Core Design Contradiction:
ReliabilityVSProductivity

Solution Approach 1:

Instead of performing full model fine-tuning, the invention applies partial action by training only a subset of parameters. This partial training approach achieves sufficient model performance for the new task while dramatically reducing computational requirements and training time, effectively resolving the contradiction between performance and training efficiency.

Inventive Principle:
Principle #16Partial or excessive action

Solution Approach 2:

The parameter space is segmented into trainable and frozen portions, allowing the training process to focus computational resources only on the necessary subset of parameters. This segmentation enables the model to achieve good performance on new tasks with significantly reduced computational cost and training time compared to full fine-tuning.

Inventive Principle:
Principle #1Segmentation

Data Source

PatentEP4682770A1Methods for adapting a model to a new task
Publication Date: 2026.01.21 TOYOTA JIDOSHA KK
  • EP4682770A1 patent drawingFigure 1~2
  • EP4682770A1 patent drawingFigure 3~4
  • EP4682770A1 patent drawing

AI summary

A computer-implemented method for adapting a machine learning model to a new task is provided. The method comprises steps of: (S10) providing a model that is pre-trained for a base task, wherein the model is a transformer-based machine learning model comprising a plurality of attention heads; (S20) selecting one or more relevant attention heads among the plurality of attention heads, wherein the relevant attention heads are relevant for performing a new task; and (S30) adapting the model to the new task by updating, among the parameters of the model, only parameters of the relevant attention heads.