Does the Definition of Difficulty Matter? Scoring Functions and their Role for Curriculum Learning

Note

Accepted at IJCNN 2026.

This repository contains the configurations and code to reproduce the experiments and analyses of the paper "Does the Definition of Difficulty Matter? Scoring Functions and their Role for Curriculum Learning". The implementation is based on aucurriculum v0.1.0 and autrainer v0.4.0.

Implemented by Simon David Noel Rampp with contributions by Manuel Milling and Andreas Triantafyllopoulos.

Experiment Reproduction

After cloning the repository and navigating to the root directory, create a virtual environment and install the dependencies:

pip install aucurriculum==0.1.0

The experiments are organized in the cifar and dcase directories (the following steps should be executed for each dataset separately). To reproduce the experiments, navigate to the respective directory:

cd cifar # for CIFAR-10cd dcase # for DCASE2020

Fetch the data and models and preprocess the dataset:

aucurriculum fetch -cn train
aucurriculum preprocess -cn train # only for DCASE2020

Launch the intial grid search and seed baselines training:

aucurriculum train -cn train
aucurriculum train -cn train_baselines

Launch the curriculum scoring function calculation:

aucurriculum score -cn curriculum
aucurriculum score -cn curriculum_agg_seed

Launch the curriculum training:

aucurriculum train -cn cl
aucurriculum train -cn cl_agg_seed

Postprocess the results:

aucurriculum postprocess results <dataset> -a seed

To reproduce the analyses, tables, and figures, execute the respective notebooks in the root directory of the repository.

Citation

If you use this code or aucurriculum in your research, please cite the following paper:

@misc{rampp2024sampledifficulty,
doi = {10.48550/ARXIV.2411.00973},
url = {https://arxiv.org/abs/2411.00973},
author = {Rampp, Simon and Milling, Manuel and Triantafyllopoulos, Andreas and Schuller, Bj\"{o}rn W.},
keywords = {Machine Learning (cs.LG), FOS: Computer and information sciences, FOS: Computer and information sciences},
title = {Does the Definition of Difficulty Matter? Scoring Functions and their Role for Curriculum Learning},
publisher = {arXiv},
year = {2024},
copyright = {Creative Commons Attribution Non Commercial Share Alike 4.0 International}
}

Does the Definition of Difficulty Matter? Scoring Functions and their Role for Curriculum Learning

Note

Accepted at IJCNN 2026.

This repository contains the configurations and code to reproduce the experiments and analyses of the paper "Does the Definition of Difficulty Matter? Scoring Functions and their Role for Curriculum Learning". The implementation is based on aucurriculum v0.1.0 and autrainer v0.4.0.

Implemented by Simon David Noel Rampp with contributions by Manuel Milling and Andreas Triantafyllopoulos.

Experiment Reproduction

After cloning the repository and navigating to the root directory, create a virtual environment and install the dependencies:

pip install aucurriculum==0.1.0

The experiments are organized in the cifar and dcase directories (the following steps should be executed for each dataset separately). To reproduce the experiments, navigate to the respective directory:

cd cifar # for CIFAR-10cd dcase # for DCASE2020

Fetch the data and models and preprocess the dataset:

aucurriculum fetch -cn train
aucurriculum preprocess -cn train # only for DCASE2020

Launch the intial grid search and seed baselines training:

aucurriculum train -cn train
aucurriculum train -cn train_baselines

Launch the curriculum scoring function calculation:

aucurriculum score -cn curriculum
aucurriculum score -cn curriculum_agg_seed

Launch the curriculum training:

aucurriculum train -cn cl
aucurriculum train -cn cl_agg_seed

Postprocess the results:

aucurriculum postprocess results <dataset> -a seed

To reproduce the analyses, tables, and figures, execute the respective notebooks in the root directory of the repository.

Citation

If you use this code or aucurriculum in your research, please cite the following paper:

@misc{rampp2024sampledifficulty,
doi = {10.48550/ARXIV.2411.00973},
url = {https://arxiv.org/abs/2411.00973},
author = {Rampp, Simon and Milling, Manuel and Triantafyllopoulos, Andreas and Schuller, Bj\"{o}rn W.},
keywords = {Machine Learning (cs.LG), FOS: Computer and information sciences, FOS: Computer and information sciences},
title = {Does the Definition of Difficulty Matter? Scoring Functions and their Role for Curriculum Learning},
publisher = {arXiv},
year = {2024},
copyright = {Creative Commons Attribution Non Commercial Share Alike 4.0 International}
}

Does the Definition of Difficulty Matter? Scoring Functions and their Role for Curriculum Learning

Note

Accepted at IJCNN 2026.

This repository contains the configurations and code to reproduce the experiments and analyses of the paper "Does the Definition of Difficulty Matter? Scoring Functions and their Role for Curriculum Learning". The implementation is based on aucurriculum v0.1.0 and autrainer v0.4.0.

Implemented by Simon David Noel Rampp with contributions by Manuel Milling and Andreas Triantafyllopoulos.

Experiment Reproduction

After cloning the repository and navigating to the root directory, create a virtual environment and install the dependencies:

pip install aucurriculum==0.1.0

The experiments are organized in the cifar and dcase directories (the following steps should be executed for each dataset separately). To reproduce the experiments, navigate to the respective directory:

cd cifar # for CIFAR-10cd dcase # for DCASE2020

Fetch the data and models and preprocess the dataset:

aucurriculum fetch -cn train
aucurriculum preprocess -cn train # only for DCASE2020

Launch the intial grid search and seed baselines training:

aucurriculum train -cn train
aucurriculum train -cn train_baselines

Launch the curriculum scoring function calculation:

aucurriculum score -cn curriculum
aucurriculum score -cn curriculum_agg_seed

Launch the curriculum training:

aucurriculum train -cn cl
aucurriculum train -cn cl_agg_seed

Postprocess the results:

aucurriculum postprocess results <dataset> -a seed

To reproduce the analyses, tables, and figures, execute the respective notebooks in the root directory of the repository.

Citation

If you use this code or aucurriculum in your research, please cite the following paper:

@misc{rampp2024sampledifficulty,
doi = {10.48550/ARXIV.2411.00973},
url = {https://arxiv.org/abs/2411.00973},
author = {Rampp, Simon and Milling, Manuel and Triantafyllopoulos, Andreas and Schuller, Bj\"{o}rn W.},
keywords = {Machine Learning (cs.LG), FOS: Computer and information sciences, FOS: Computer and information sciences},
title = {Does the Definition of Difficulty Matter? Scoring Functions and their Role for Curriculum Learning},
publisher = {arXiv},
year = {2024},
copyright = {Creative Commons Attribution Non Commercial Share Alike 4.0 International}
}

Does the Definition of Difficulty Matter? Scoring Functions and their Role for Curriculum Learning

Note

Accepted at IJCNN 2026.

This repository contains the configurations and code to reproduce the experiments and analyses of the paper "Does the Definition of Difficulty Matter? Scoring Functions and their Role for Curriculum Learning". The implementation is based on aucurriculum v0.1.0 and autrainer v0.4.0.

Implemented by Simon David Noel Rampp with contributions by Manuel Milling and Andreas Triantafyllopoulos.

Experiment Reproduction

After cloning the repository and navigating to the root directory, create a virtual environment and install the dependencies:

pip install aucurriculum==0.1.0

The experiments are organized in the cifar and dcase directories (the following steps should be executed for each dataset separately). To reproduce the experiments, navigate to the respective directory:

cd cifar # for CIFAR-10cd dcase # for DCASE2020

Fetch the data and models and preprocess the dataset:

aucurriculum fetch -cn train
aucurriculum preprocess -cn train # only for DCASE2020

Launch the intial grid search and seed baselines training:

aucurriculum train -cn train
aucurriculum train -cn train_baselines

Launch the curriculum scoring function calculation:

aucurriculum score -cn curriculum
aucurriculum score -cn curriculum_agg_seed

Launch the curriculum training:

aucurriculum train -cn cl
aucurriculum train -cn cl_agg_seed

Postprocess the results:

aucurriculum postprocess results <dataset> -a seed

To reproduce the analyses, tables, and figures, execute the respective notebooks in the root directory of the repository.

Citation

If you use this code or aucurriculum in your research, please cite the following paper:

@misc{rampp2024sampledifficulty,
doi = {10.48550/ARXIV.2411.00973},
url = {https://arxiv.org/abs/2411.00973},
author = {Rampp, Simon and Milling, Manuel and Triantafyllopoulos, Andreas and Schuller, Bj\"{o}rn W.},
keywords = {Machine Learning (cs.LG), FOS: Computer and information sciences, FOS: Computer and information sciences},
title = {Does the Definition of Difficulty Matter? Scoring Functions and their Role for Curriculum Learning},
publisher = {arXiv},
year = {2024},
copyright = {Creative Commons Attribution Non Commercial Share Alike 4.0 International}
}

Does the Definition of Difficulty Matter? Scoring Functions and their Role for Curriculum Learning

Note

Accepted at IJCNN 2026.

This repository contains the configurations and code to reproduce the experiments and analyses of the paper "Does the Definition of Difficulty Matter? Scoring Functions and their Role for Curriculum Learning". The implementation is based on aucurriculum v0.1.0 and autrainer v0.4.0.

Implemented by Simon David Noel Rampp with contributions by Manuel Milling and Andreas Triantafyllopoulos.

Experiment Reproduction

After cloning the repository and navigating to the root directory, create a virtual environment and install the dependencies:

pip install aucurriculum==0.1.0

The experiments are organized in the cifar and dcase directories (the following steps should be executed for each dataset separately). To reproduce the experiments, navigate to the respective directory:

cd cifar # for CIFAR-10cd dcase # for DCASE2020

Fetch the data and models and preprocess the dataset:

aucurriculum fetch -cn train
aucurriculum preprocess -cn train # only for DCASE2020

Launch the intial grid search and seed baselines training:

aucurriculum train -cn train
aucurriculum train -cn train_baselines

Launch the curriculum scoring function calculation:

aucurriculum score -cn curriculum
aucurriculum score -cn curriculum_agg_seed

Launch the curriculum training:

aucurriculum train -cn cl
aucurriculum train -cn cl_agg_seed

Postprocess the results:

aucurriculum postprocess results <dataset> -a seed

To reproduce the analyses, tables, and figures, execute the respective notebooks in the root directory of the repository.

Citation

If you use this code or aucurriculum in your research, please cite the following paper:

@misc{rampp2024sampledifficulty,
doi = {10.48550/ARXIV.2411.00973},
url = {https://arxiv.org/abs/2411.00973},
author = {Rampp, Simon and Milling, Manuel and Triantafyllopoulos, Andreas and Schuller, Bj\"{o}rn W.},
keywords = {Machine Learning (cs.LG), FOS: Computer and information sciences, FOS: Computer and information sciences},
title = {Does the Definition of Difficulty Matter? Scoring Functions and their Role for Curriculum Learning},
publisher = {arXiv},
year = {2024},
copyright = {Creative Commons Attribution Non Commercial Share Alike 4.0 International}
}

Does the Definition of Difficulty Matter? Scoring Functions and their Role for Curriculum Learning

Note

Accepted at IJCNN 2026.

This repository contains the configurations and code to reproduce the experiments and analyses of the paper "Does the Definition of Difficulty Matter? Scoring Functions and their Role for Curriculum Learning". The implementation is based on aucurriculum v0.1.0 and autrainer v0.4.0.

Implemented by Simon David Noel Rampp with contributions by Manuel Milling and Andreas Triantafyllopoulos.

Experiment Reproduction

After cloning the repository and navigating to the root directory, create a virtual environment and install the dependencies:

pip install aucurriculum==0.1.0

The experiments are organized in the cifar and dcase directories (the following steps should be executed for each dataset separately). To reproduce the experiments, navigate to the respective directory:

cd cifar # for CIFAR-10cd dcase # for DCASE2020

Fetch the data and models and preprocess the dataset:

aucurriculum fetch -cn train
aucurriculum preprocess -cn train # only for DCASE2020

Launch the intial grid search and seed baselines training:

aucurriculum train -cn train
aucurriculum train -cn train_baselines

Launch the curriculum scoring function calculation:

aucurriculum score -cn curriculum
aucurriculum score -cn curriculum_agg_seed

Launch the curriculum training:

aucurriculum train -cn cl
aucurriculum train -cn cl_agg_seed

Postprocess the results:

aucurriculum postprocess results <dataset> -a seed

To reproduce the analyses, tables, and figures, execute the respective notebooks in the root directory of the repository.

Citation

If you use this code or aucurriculum in your research, please cite the following paper:

@misc{rampp2024sampledifficulty,
doi = {10.48550/ARXIV.2411.00973},
url = {https://arxiv.org/abs/2411.00973},
author = {Rampp, Simon and Milling, Manuel and Triantafyllopoulos, Andreas and Schuller, Bj\"{o}rn W.},
keywords = {Machine Learning (cs.LG), FOS: Computer and information sciences, FOS: Computer and information sciences},
title = {Does the Definition of Difficulty Matter? Scoring Functions and their Role for Curriculum Learning},
publisher = {arXiv},
year = {2024},
copyright = {Creative Commons Attribution Non Commercial Share Alike 4.0 International}
}

Does the Definition of Difficulty Matter? Scoring Functions and their Role for Curriculum Learning

Note

Accepted at IJCNN 2026.

This repository contains the configurations and code to reproduce the experiments and analyses of the paper "Does the Definition of Difficulty Matter? Scoring Functions and their Role for Curriculum Learning". The implementation is based on aucurriculum v0.1.0 and autrainer v0.4.0.

Implemented by Simon David Noel Rampp with contributions by Manuel Milling and Andreas Triantafyllopoulos.

Experiment Reproduction

After cloning the repository and navigating to the root directory, create a virtual environment and install the dependencies:

pip install aucurriculum==0.1.0

The experiments are organized in the cifar and dcase directories (the following steps should be executed for each dataset separately). To reproduce the experiments, navigate to the respective directory:

cd cifar # for CIFAR-10cd dcase # for DCASE2020

Fetch the data and models and preprocess the dataset:

aucurriculum fetch -cn train
aucurriculum preprocess -cn train # only for DCASE2020

Launch the intial grid search and seed baselines training:

aucurriculum train -cn train
aucurriculum train -cn train_baselines

Launch the curriculum scoring function calculation:

aucurriculum score -cn curriculum
aucurriculum score -cn curriculum_agg_seed

Launch the curriculum training:

aucurriculum train -cn cl
aucurriculum train -cn cl_agg_seed

Postprocess the results:

aucurriculum postprocess results <dataset> -a seed

To reproduce the analyses, tables, and figures, execute the respective notebooks in the root directory of the repository.

Citation

If you use this code or aucurriculum in your research, please cite the following paper:

@misc{rampp2024sampledifficulty,
doi = {10.48550/ARXIV.2411.00973},
url = {https://arxiv.org/abs/2411.00973},
author = {Rampp, Simon and Milling, Manuel and Triantafyllopoulos, Andreas and Schuller, Bj\"{o}rn W.},
keywords = {Machine Learning (cs.LG), FOS: Computer and information sciences, FOS: Computer and information sciences},
title = {Does the Definition of Difficulty Matter? Scoring Functions and their Role for Curriculum Learning},
publisher = {arXiv},
year = {2024},
copyright = {Creative Commons Attribution Non Commercial Share Alike 4.0 International}
}

Does the Definition of Difficulty Matter? Scoring Functions and their Role for Curriculum Learning

Note

Accepted at IJCNN 2026.

This repository contains the configurations and code to reproduce the experiments and analyses of the paper "Does the Definition of Difficulty Matter? Scoring Functions and their Role for Curriculum Learning". The implementation is based on aucurriculum v0.1.0 and autrainer v0.4.0.

Implemented by Simon David Noel Rampp with contributions by Manuel Milling and Andreas Triantafyllopoulos.

Experiment Reproduction

After cloning the repository and navigating to the root directory, create a virtual environment and install the dependencies:

pip install aucurriculum==0.1.0

The experiments are organized in the cifar and dcase directories (the following steps should be executed for each dataset separately). To reproduce the experiments, navigate to the respective directory:

cd cifar # for CIFAR-10cd dcase # for DCASE2020

Fetch the data and models and preprocess the dataset:

aucurriculum fetch -cn train
aucurriculum preprocess -cn train # only for DCASE2020

Launch the intial grid search and seed baselines training:

aucurriculum train -cn train
aucurriculum train -cn train_baselines

Launch the curriculum scoring function calculation:

aucurriculum score -cn curriculum
aucurriculum score -cn curriculum_agg_seed

Launch the curriculum training:

aucurriculum train -cn cl
aucurriculum train -cn cl_agg_seed

Postprocess the results:

aucurriculum postprocess results <dataset> -a seed

To reproduce the analyses, tables, and figures, execute the respective notebooks in the root directory of the repository.

Citation

If you use this code or aucurriculum in your research, please cite the following paper:

@misc{rampp2024sampledifficulty,
doi = {10.48550/ARXIV.2411.00973},
url = {https://arxiv.org/abs/2411.00973},
author = {Rampp, Simon and Milling, Manuel and Triantafyllopoulos, Andreas and Schuller, Bj\"{o}rn W.},
keywords = {Machine Learning (cs.LG), FOS: Computer and information sciences, FOS: Computer and information sciences},
title = {Does the Definition of Difficulty Matter? Scoring Functions and their Role for Curriculum Learning},
publisher = {arXiv},
year = {2024},
copyright = {Creative Commons Attribution Non Commercial Share Alike 4.0 International}
}

Name		Name	Last commit message	Last commit date
cifar		cifar
dcase		dcase
.gitignore		.gitignore
4_a_baselines.ipynb		4_a_baselines.ipynb
4_b_1_impact_hparams.ipynb		4_b_1_impact_hparams.ipynb
4_b_2_robustness_ensemble.ipynb		4_b_2_robustness_ensemble.ipynb
4_b_3_difficulty_distributions.ipynb		4_b_3_difficulty_distributions.ipynb
4_b_4_difficulty_agreement.ipynb		4_b_4_difficulty_agreement.ipynb
4_c_1_ordering_pacing.ipynb		4_c_1_ordering_pacing.ipynb
4_c_2_robust_curriculum.ipynb		4_c_2_robust_curriculum.ipynb
4_c_3_scoring_performance.ipynb		4_c_3_scoring_performance.ipynb
4_c_4_fusion_performance.ipynb		4_c_4_fusion_performance.ipynb
LICENSE		LICENSE
README.md		README.md

Name		Name	Last commit message	Last commit date
cifar		cifar
dcase		dcase
.gitignore		.gitignore
4_a_baselines.ipynb		4_a_baselines.ipynb
4_b_1_impact_hparams.ipynb		4_b_1_impact_hparams.ipynb
4_b_2_robustness_ensemble.ipynb		4_b_2_robustness_ensemble.ipynb
4_b_3_difficulty_distributions.ipynb		4_b_3_difficulty_distributions.ipynb
4_b_4_difficulty_agreement.ipynb		4_b_4_difficulty_agreement.ipynb
4_c_1_ordering_pacing.ipynb		4_c_1_ordering_pacing.ipynb
4_c_2_robust_curriculum.ipynb		4_c_2_robust_curriculum.ipynb
4_c_3_scoring_performance.ipynb		4_c_3_scoring_performance.ipynb
4_c_4_fusion_performance.ipynb		4_c_4_fusion_performance.ipynb
LICENSE		LICENSE
README.md		README.md

Name		Name	Last commit message	Last commit date
cifar		cifar
dcase		dcase
.gitignore		.gitignore
4_a_baselines.ipynb		4_a_baselines.ipynb
4_b_1_impact_hparams.ipynb		4_b_1_impact_hparams.ipynb
4_b_2_robustness_ensemble.ipynb		4_b_2_robustness_ensemble.ipynb
4_b_3_difficulty_distributions.ipynb		4_b_3_difficulty_distributions.ipynb
4_b_4_difficulty_agreement.ipynb		4_b_4_difficulty_agreement.ipynb
4_c_1_ordering_pacing.ipynb		4_c_1_ordering_pacing.ipynb
4_c_2_robust_curriculum.ipynb		4_c_2_robust_curriculum.ipynb
4_c_3_scoring_performance.ipynb		4_c_3_scoring_performance.ipynb
4_c_4_fusion_performance.ipynb		4_c_4_fusion_performance.ipynb
LICENSE		LICENSE
README.md		README.md

Name		Name	Last commit message	Last commit date
cifar		cifar
dcase		dcase
.gitignore		.gitignore
4_a_baselines.ipynb		4_a_baselines.ipynb
4_b_1_impact_hparams.ipynb		4_b_1_impact_hparams.ipynb
4_b_2_robustness_ensemble.ipynb		4_b_2_robustness_ensemble.ipynb
4_b_3_difficulty_distributions.ipynb		4_b_3_difficulty_distributions.ipynb
4_b_4_difficulty_agreement.ipynb		4_b_4_difficulty_agreement.ipynb
4_c_1_ordering_pacing.ipynb		4_c_1_ordering_pacing.ipynb
4_c_2_robust_curriculum.ipynb		4_c_2_robust_curriculum.ipynb
4_c_3_scoring_performance.ipynb		4_c_3_scoring_performance.ipynb
4_c_4_fusion_performance.ipynb		4_c_4_fusion_performance.ipynb
LICENSE		LICENSE
README.md		README.md

Name		Name	Last commit message	Last commit date
cifar		cifar
dcase		dcase
.gitignore		.gitignore
4_a_baselines.ipynb		4_a_baselines.ipynb
4_b_1_impact_hparams.ipynb		4_b_1_impact_hparams.ipynb
4_b_2_robustness_ensemble.ipynb		4_b_2_robustness_ensemble.ipynb
4_b_3_difficulty_distributions.ipynb		4_b_3_difficulty_distributions.ipynb
4_b_4_difficulty_agreement.ipynb		4_b_4_difficulty_agreement.ipynb
4_c_1_ordering_pacing.ipynb		4_c_1_ordering_pacing.ipynb
4_c_2_robust_curriculum.ipynb		4_c_2_robust_curriculum.ipynb
4_c_3_scoring_performance.ipynb		4_c_3_scoring_performance.ipynb
4_c_4_fusion_performance.ipynb		4_c_4_fusion_performance.ipynb
LICENSE		LICENSE
README.md		README.md

Latest commit

History

Folders and files

Repository files navigation

Does the Definition of Difficulty Matter? Scoring Functions and their Role for Curriculum Learning

Experiment Reproduction

Citation

About

Resources

Stars

Watchers

Forks

Contributors

Languages

Latest commit

History

Folders and files

Repository files navigation

Does the Definition of Difficulty Matter? Scoring Functions and their Role for Curriculum Learning

Experiment Reproduction

Citation

About

Resources

Stars

Watchers

Forks

Contributors

Languages

Latest commit

History

Folders and files

Repository files navigation

Does the Definition of Difficulty Matter? Scoring Functions and their Role for Curriculum Learning

Experiment Reproduction

Citation

About

Resources

Stars

Watchers

Forks

Contributors

Languages

Latest commit

History

Folders and files

Repository files navigation

Does the Definition of Difficulty Matter? Scoring Functions and their Role for Curriculum Learning

Experiment Reproduction

Citation

About

Resources

Stars

Watchers

Forks

Contributors

Languages

Latest commit

History

Folders and files

Repository files navigation

Does the Definition of Difficulty Matter? Scoring Functions and their Role for Curriculum Learning

Experiment Reproduction

Citation

About

Resources

Stars

Watchers

Forks

Contributors

Languages

Latest commit

History

Folders and files

Repository files navigation

Does the Definition of Difficulty Matter? Scoring Functions and their Role for Curriculum Learning

Experiment Reproduction

Citation

About

Resources

Stars