Diverse Prototypical Ensembles Improve Robustness to Subpopulation Shift

• URL: http://arxiv.org/abs/2505.23027v1
• Date: Thu, 29 May 2025 03:12:56 GMT
• Title: Diverse Prototypical Ensembles Improve Robustness to Subpopulation Shift
• Authors: Minh Nguyen Nhat To, Paul F RWilson, Viet Nguyen, Mohamed Harmanani, Michael Cooper, Fahimeh Fooladgar, Purang Abolmaesumi, Parvin Mousavi, Rahul G. Krishnan,
• Abstract summary: Subpopulationtion shift can significantly degrade the performance of machine learning models.<n>We propose using an ensemble of diverse classifiers to adaptively capture risk associated with subpopulations.<n>Our method of Diverse Prototypical Ensembles (DPEs) often outperforms the prior state-of-the-art in worst-group accuracy.
• Score: 10.04893653044606
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The subpopulationtion shift, characterized by a disparity in subpopulation distributibetween theween the training and target datasets, can significantly degrade the performance of machine learning models. Current solutions to subpopulation shift involve modifying empirical risk minimization with re-weighting strategies to improve generalization. This strategy relies on assumptions about the number and nature of subpopulations and annotations on group membership, which are unavailable for many real-world datasets. Instead, we propose using an ensemble of diverse classifiers to adaptively capture risk associated with subpopulations. Given a feature extractor network, we replace its standard linear classification layer with a mixture of prototypical classifiers, where each member is trained to classify the data while focusing on different features and samples from other members. In empirical evaluation on nine real-world datasets, covering diverse domains and kinds of subpopulation shift, our method of Diverse Prototypical Ensembles (DPEs) often outperforms the prior state-of-the-art in worst-group accuracy. The code is available at https://github.com/minhto2802/dpe4subpop

Related papers

• Minimax Regret Learning for Data with Heterogeneous Subgroups [12.253779655660571]
  We develop a min-max-regret (MMR) learning framework for general supervised learning, which targets to minimize the worst-group regret. We demonstrate the effectiveness of our method through extensive simulation studies and an application to kidney transplantation data from hundreds of transplant centers.
  arXiv  Detail & Related papers  (2024-05-02T20:06:41Z)
• Class Distribution Shifts in Zero-Shot Learning: Learning Robust Representations [3.8980564330208662]
  We propose and analyze a model that assumes that the attribute responsible for the shift is unknown in advance.<n>We show that our algorithm improves generalization to diverse class distributions in both simulations and experiments on real-world datasets.
  arXiv  Detail & Related papers  (2023-11-30T14:14:31Z)
• Understanding Variation in Subpopulation Susceptibility to Poisoning Attacks [9.977765534931596]
  We investigate the properties that can impact the effectiveness of state-of-the-art poisoning attacks against different subpopulations. We find that dataset separability plays a dominant role in subpopulation vulnerability for less separable datasets. A crucial subpopulation property is captured by the difference in loss on the clean dataset between the clean model and a target model.
  arXiv  Detail & Related papers  (2023-11-20T05:35:40Z)
• Tackling Diverse Minorities in Imbalanced Classification [80.78227787608714]
  Imbalanced datasets are commonly observed in various real-world applications, presenting significant challenges in training classifiers. We propose generating synthetic samples iteratively by mixing data samples from both minority and majority classes. We demonstrate the effectiveness of our proposed framework through extensive experiments conducted on seven publicly available benchmark datasets.
  arXiv  Detail & Related papers  (2023-08-28T18:48:34Z)
• Change is Hard: A Closer Look at Subpopulation Shift [48.0369745740936]
  We propose a unified framework that dissects and explains common shifts in subgroups. We then establish a benchmark of 20 state-of-the-art algorithms evaluated on 12 real-world datasets in vision, language, and healthcare domains.
  arXiv  Detail & Related papers  (2023-02-23T18:59:56Z)
• Intra-class Adaptive Augmentation with Neighbor Correction for Deep Metric Learning [99.14132861655223]
  We propose a novel intra-class adaptive augmentation (IAA) framework for deep metric learning. We reasonably estimate intra-class variations for every class and generate adaptive synthetic samples to support hard samples mining. Our method significantly improves and outperforms the state-of-the-art methods on retrieval performances by 3%-6%.
  arXiv  Detail & Related papers  (2022-11-29T14:52:38Z)
• PLM: Partial Label Masking for Imbalanced Multi-label Classification [59.68444804243782]
  Neural networks trained on real-world datasets with long-tailed label distributions are biased towards frequent classes and perform poorly on infrequent classes. We propose a method, Partial Label Masking (PLM), which utilizes this ratio during training. Our method achieves strong performance when compared to existing methods on both multi-label (MultiMNIST and MSCOCO) and single-label (imbalanced CIFAR-10 and CIFAR-100) image classification datasets.
  arXiv  Detail & Related papers  (2021-05-22T18:07:56Z)
• Learning by Minimizing the Sum of Ranked Range [58.24935359348289]
  We introduce the sum of ranked range (SoRR) as a general approach to form learning objectives. A ranked range is a consecutive sequence of sorted values of a set of real numbers. We explore two applications in machine learning of the minimization of the SoRR framework, namely the AoRR aggregate loss for binary classification and the TKML individual loss for multi-label/multi-class classification.
  arXiv  Detail & Related papers  (2020-10-05T01:58:32Z)
• BREEDS: Benchmarks for Subpopulation Shift [98.90314444545204]
  We develop a methodology for assessing the robustness of models to subpopulation shift. We leverage the class structure underlying existing datasets to control the data subpopulations that comprise the training and test distributions. Applying this methodology to the ImageNet dataset, we create a suite of subpopulation shift benchmarks of varying granularity.
  arXiv  Detail & Related papers  (2020-08-11T17:04:47Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.