Distributionally Robust Deep Learning using Hardness Weighted Sampling

Lucas Fidon10000-0003-1450-1634, Michael Aertsen20000-0003-1994-5365, Thomas Deprest20000-0002-9196-9807, Doaa Emam30000-0002-3784-8174, Frédéric Guffens2, Nada Mufti40000-0001-9839-8085, Esther Van Elslander2, Ernst Schwartz50000-0002-7518-2035, Michael Ebner40000-0002-0170-7062, Daniela Prayer50000-0003-4612-2356, Gregor Kasprian50000-0003-3858-3347, Anna L David60000-0002-0199-6140, Andrew Melbourne40000-0001-7667-3947, Sébastien Ourselin40000-0002-5694-5340, Jan Deprest30000-0002-4920-945X, Georg Langs50000-0002-5536-6873, Tom Vercauteren40000-0003-1794-0456
1: Shool of Biomedical Engineering & Imaging Sciences, King's College London, 2: Department of Radiology, University Hospitals Leuven, 3: Department of Obstetrics and Gynaecology, University Hospitals Leuven, 4: School of Biomedical Engineering & Imaging Sciences, King’s College London, 5: Department of Biomedical Imaging and Image-guided Therapy, Medical University of Vienna, 6: Institute for Women’s Health, University College London
Publication date: 2022/07/18
https://doi.org/10.59275/j.melba.2022-8b6a
PDF · Code · Video · arXiv

Abstract

Limiting failures of machine learning systems is of paramount importance for safety-critical applications. In order to improve the robustness of machine learning systems, Distributionally Robust Optimization (DRO) has been proposed as a generalization of Empirical Risk Minimization (ERM). However, its use in deep learning has been severely restricted due to the relative inefficiency of the optimizers available for DRO in comparison to the wide-spread variants of Stochastic Gradient Descent (SGD) optimizers for ERM.
We propose SGD with hardness weighted sampling, a principled and efficient optimization method for DRO in machine learning that is particularly suited in the context of deep learning. Similar to a hard example mining strategy in practice, the proposed algorithm is straightforward to implement and computationally as efficient as SGD-based optimizers used for deep learning, requiring minimal overhead computation. In contrast to typical ad hoc hard mining approaches, we prove the convergence of our DRO algorithm for over-parameterized deep learning networks with ReLU activation and finite number of layers and parameters.
Our experiments on fetal brain 3D MRI segmentation and brain tumor segmentation in MRI demonstrate the feasibility and the usefulness of our approach. Using our hardness weighted sampling for training a state-of-the-art deep learning pipeline leads to improved robustness to anatomical variabilities in automatic fetal brain 3D MRI segmentation using deep learning and to improved robustness to the image protocol variations in brain tumor segmentation.a decrease of 2% of the interquartile range of the Dice scores for the enhanced tumor and the tumor core regions.
Our code is available at https://github.com/LucasFidon/HardnessWeightedSampler

Keywords

Machine Learning · Image Segmentation · Distributionally Robust Optimization

Bibtex @article{melba:2022:019:fidon, title = "Distributionally Robust Deep Learning using Hardness Weighted Sampling", author = "Fidon, Lucas and Aertsen, Michael and Deprest, Thomas and Emam, Doaa and Guffens, Frédéric and Mufti, Nada and Van Elslander, Esther and Schwartz, Ernst and Ebner, Michael and Prayer, Daniela and Kasprian, Gregor and David, Anna L and Melbourne, Andrew and Ourselin, Sébastien and Deprest, Jan and Langs, Georg and Vercauteren, Tom", journal = "Machine Learning for Biomedical Imaging", volume = "1", issue = "PIPPI 2021 special issue", year = "2022", pages = "1--61", issn = "2766-905X", doi = "https://doi.org/10.59275/j.melba.2022-8b6a", url = "https://melba-journal.org/2022:019" }
RISTY - JOUR AU - Fidon, Lucas AU - Aertsen, Michael AU - Deprest, Thomas AU - Emam, Doaa AU - Guffens, Frédéric AU - Mufti, Nada AU - Van Elslander, Esther AU - Schwartz, Ernst AU - Ebner, Michael AU - Prayer, Daniela AU - Kasprian, Gregor AU - David, Anna L AU - Melbourne, Andrew AU - Ourselin, Sébastien AU - Deprest, Jan AU - Langs, Georg AU - Vercauteren, Tom PY - 2022 TI - Distributionally Robust Deep Learning using Hardness Weighted Sampling T2 - Machine Learning for Biomedical Imaging VL - 1 IS - PIPPI 2021 special issue SP - 1 EP - 61 SN - 2766-905X DO - https://doi.org/10.59275/j.melba.2022-8b6a UR - https://melba-journal.org/2022:019 ER -

2022:019 cover