When resampling/reweighting improves feature learning in imbalanced classification?: A toy-model study

• URL: http://arxiv.org/abs/2409.05598v1
• Date: Mon, 9 Sep 2024 13:31:00 GMT
• Title: When resampling/reweighting improves feature learning in imbalanced classification?: A toy-model study
• Authors: Tomoyuki Obuchi, Toshiyuki Tanaka,
• Abstract summary: A toy model of binary classification is studied with the aim of clarifying the class-wise resampling/reweighting effect on the feature learning performance under the presence of class imbalance. The result shows that there exists a case in which the no resampling/reweighting situation gives the best feature learning performance irrespective of the choice of losses or classifiers.
• Score: 5.5730368125641405
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: A toy model of binary classification is studied with the aim of clarifying the class-wise resampling/reweighting effect on the feature learning performance under the presence of class imbalance. In the analysis, a high-dimensional limit of the feature is taken while keeping the dataset size ratio against the feature dimension finite and the non-rigorous replica method from statistical mechanics is employed. The result shows that there exists a case in which the no resampling/reweighting situation gives the best feature learning performance irrespectively of the choice of losses or classifiers, supporting recent findings in Cao et al. (2019); Kang et al. (2019). It is also revealed that the key of the result is the symmetry of the loss and the problem setting. Inspired by this, we propose a further simplified model exhibiting the same property for the multiclass setting. These clarify when the class-wise resampling/reweighting becomes effective in imbalanced classification.

Related papers

• Granularity Matters in Long-Tail Learning [62.30734737735273]
  We offer a novel perspective on long-tail learning, inspired by an observation: datasets with finer granularity tend to be less affected by data imbalance. We introduce open-set auxiliary classes that are visually similar to existing ones, aiming to enhance representation learning for both head and tail classes. To prevent the overwhelming presence of auxiliary classes from disrupting training, we introduce a neighbor-silencing loss.
  arXiv  Detail & Related papers  (2024-10-21T13:06:21Z)
• Bias Mitigating Few-Shot Class-Incremental Learning [17.185744533050116]
  Few-shot class-incremental learning aims at recognizing novel classes continually with limited novel class samples. Recent methods somewhat alleviate the accuracy imbalance between base and incremental classes by fine-tuning the feature extractor in the incremental sessions. We propose a novel method to mitigate model bias of the FSCIL problem during training and inference processes.
  arXiv  Detail & Related papers  (2024-02-01T10:37:41Z)
• Boosting Differentiable Causal Discovery via Adaptive Sample Reweighting [62.23057729112182]
  Differentiable score-based causal discovery methods learn a directed acyclic graph from observational data. We propose a model-agnostic framework to boost causal discovery performance by dynamically learning the adaptive weights for the Reweighted Score function, ReScore.
  arXiv  Detail & Related papers  (2023-03-06T14:49:59Z)
• Leveraging Angular Information Between Feature and Classifier for Long-tailed Learning: A Prediction Reformulation Approach [90.77858044524544]
  We reformulate the recognition probabilities through included angles without re-balancing the classifier weights. Inspired by the performance improvement of the predictive form reformulation, we explore the different properties of this angular prediction. Our method is able to obtain the best performance among peer methods without pretraining on CIFAR10/100-LT and ImageNet-LT.
  arXiv  Detail & Related papers  (2022-12-03T07:52:48Z)
• Neural Collapse Inspired Attraction-Repulsion-Balanced Loss for Imbalanced Learning [97.81549071978789]
  We propose Attraction-Repulsion-Balanced Loss (ARB-Loss) to balance the different components of the gradients. We perform experiments on the large-scale classification and segmentation datasets and our ARB-Loss can achieve state-of-the-art performance.
  arXiv  Detail & Related papers  (2022-04-19T08:23:23Z)
• Learning Debiased and Disentangled Representations for Semantic Segmentation [52.35766945827972]
  We propose a model-agnostic and training scheme for semantic segmentation. By randomly eliminating certain class information in each training iteration, we effectively reduce feature dependencies among classes. Models trained with our approach demonstrate strong results on multiple semantic segmentation benchmarks.
  arXiv  Detail & Related papers  (2021-10-31T16:15:09Z)
• An Empirical Study on the Joint Impact of Feature Selection and Data Resampling on Imbalance Classification [4.506770920842088]
  This study focuses on the synergy between feature selection and data resampling for imbalance classification. We conduct a large amount of experiments on 52 publicly available datasets, using 9 feature selection methods, 6 resampling approaches for class imbalance learning, and 3 well-known classification algorithms.
  arXiv  Detail & Related papers  (2021-09-01T06:01:51Z)
• How Nonconformity Functions and Difficulty of Datasets Impact the Efficiency of Conformal Classifiers [0.1611401281366893]
  In conformal classification, the systems can output multiple class labels instead of one. For a Neural Network-based conformal classifier, the inverse probability allows minimizing the average number of predicted labels. We propose a successful method to combine the properties of these two nonconformity functions.
  arXiv  Detail & Related papers  (2021-08-12T11:50:12Z)
• Statistical Theory for Imbalanced Binary Classification [8.93993657323783]
  We show that optimal classification performance depends on certain properties of class imbalance that have not previously been formalized. Specifically, we propose a novel sub-type of class imbalance, which we call Uniform Class Imbalance. These results provide some of the first meaningful finite-sample statistical theory for imbalanced binary classification.
  arXiv  Detail & Related papers  (2021-07-05T03:55:43Z)
• Imbalanced Image Classification with Complement Cross Entropy [10.35173901214638]
  We study the study of cross entropy which mostly ignores output scores on incorrect classes. This work discovers that predicted probabilities on incorrect classes improves the prediction accuracy for imbalanced image classification. The proposed loss makes the ground truth class overwhelm the other classes in terms of softmax probability.
  arXiv  Detail & Related papers  (2020-09-04T13:46:24Z)
• Long-Tailed Recognition Using Class-Balanced Experts [128.73438243408393]
  We propose an ensemble of class-balanced experts that combines the strength of diverse classifiers. Our ensemble of class-balanced experts reaches results close to state-of-the-art and an extended ensemble establishes a new state-of-the-art on two benchmarks for long-tailed recognition.
  arXiv  Detail & Related papers  (2020-04-07T20:57:44Z)

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.