اشترك بالحزمة الذهبية واحصل على وصول غير محدود شمرا أكاديميا
تسجيل مستخدم جديدA Flexible and Adaptive Framework for Abstention Under Class Imbalance
41
0
0.0
(
0
)
اسأل ChatGPT حول البحث
ﻻ يوجد ملخص باللغة العربية
In practical applications of machine learning, it is often desirable to identify and abstain on examples where the models predictions are likely to be incorrect. Much of the prior work on this topic focused on out-of-distribution detection or performance metrics such as top-k accuracy. Comparatively little attention was given to metrics such as area-under-the-curve or Cohens Kappa, which are extremely relevant for imbalanced datasets. Abstention strategies aimed at top-k accuracy can produce poor results on these metrics when applied to imbalanced datasets, even when all examples are in-distribution. We propose a framework to address this gap. Our framework leverages the insight that calibrated probability estimates can be used as a proxy for the true class labels, thereby allowing us to estimate the change in an arbitrary metric if an example were abstained on. Using this framework, we derive computationally efficient metric-specific abstention algorithms for optimizing the sensitivity at a target specificity level, the area under the ROC, and the weighted Cohens Kappa. Because our method relies only on calibrated probability estimates, we further show that by leveraging recent work on domain adaptation under label shift, we can generalize to test-set distributions that may have a different class imbalance compared to the training set distribution. On various experiments involving medical imaging, natural language processing, computer vision and genomics, we demonstrate the effectiveness of our approach. Source code available at https://github.com/blindauth/abstention. Colab notebooks reproducing results available at https://github.com/blindauth/abstention_experiments.
قيم البحث
اقرأ أيضاً
The goal of this paper is to design image classification systems that, after an initial multi-task training phase, can automatically adapt to new tasks encountered at test time. We introduce a conditional neural process based approach to the multi-ta
sk classification setting for this purpose, and establish connections to the meta-learning and few-shot learning literature. The resulting approach, called CNAPs, comprises a classifier whose parameters are modulated by an adaptation network that takes the current tasks dataset as input. We demonstrate that CNAPs achieves state-of-the-art results on the challenging Meta-Dataset benchmark indicating high-quality transfer-learning. We show that the approach is robust, avoiding both over-fitting in low-shot regimes and under-fitting in high-shot regimes. Timing experiments reveal that CNAPs is computationally efficient at test-time as it does not involve gradient based adaptation. Finally, we show that trained models are immediately deployable to continual learning and active learning where they can outperform existing approaches that do not leverage transfer learning.
We introduce a novel method to combat label noise when training deep neural networks for classification. We propose a loss function that permits abstention during training thereby allowing the DNN to abstain on confusing samples while continuing to l
earn and improve classification performance on the non-abstained samples. We show how such a deep abstaining classifier (DAC) can be used for robust learning in the presence of different types of label noise. In the case of structured or systematic label noise -- where noisy training labels or confusing examples are correlated with underlying features of the data-- training with abstention enables representation learning for features that are associated with unreliable labels. In the case of unstructured (arbitrary) label noise, abstention during training enables the DAC to be used as an effective data cleaner by identifying samples that are likely to have label noise. We provide analytical results on the loss function behavior that enable dynamic adaption of abstention rates based on learning progress during training. We demonstrate the utility of the deep abstaining classifier for various image classification tasks under different types of label noise; in the case of arbitrary label noise, we show significant improvements over previously published results on multiple image benchmarks. Source code is available at https://github.com/thulas/dac-label-noise
The usage of unmanned aerial vehicles (UAVs) in civil and military applications continues to increase due to the numerous advantages that they provide over conventional approaches. Despite the abundance of such advantages, it is imperative to investi
gate the performance of UAV utilization while considering their design limitations. This paper investigates the deployment of UAV swarms when each UAV carries a machine learning classification task. To avoid data exchange with ground-based processing nodes, a federated learning approach is adopted between a UAV leader and the swarm members to improve the local learning model while avoiding excessive air-to-ground and ground-to-air communications. Moreover, the proposed deployment framework considers the stringent energy constraints of UAVs and the problem of class imbalance, where we show that considering these design parameters significantly improves the performances of the UAV swarm in terms of classification accuracy, energy consumption and availability of UAVs when compared with several baseline algorithms.
Important tasks like record linkage and extreme classification demonstrate extreme class imbalance, with 1 minority instance to every 1 million or more majority instances. Obtaining a sufficient sample of all classes, even just to achieve statistical
ly-significant evaluation, is so challenging that most current approaches yield poor estimates or incur impractical cost. Where importance sampling has been levied against this challenge, restrictive constraints are placed on performance metrics, estimates do not come with appropriate guarantees, or evaluations cannot adapt to incoming labels. This paper develops a framework for online evaluation based on adaptive importance sampling. Given a target performance metric and model for $p(y|x)$, the framework adapts a distribution over items to label in order to maximize statistical precision. We establish strong consistency and a central limit theorem for the resulting performance estimates, and instantiate our framework with worked examples that leverage Dirichlet-tree models. Experiments demonstrate an average MSE superior to state-of-the-art on fixed label budgets.
We develop a probabilistic framework for deep learning based on the Deep Rendering Mixture Model (DRMM), a new generative probabilistic model that explicitly capture variations in data due to latent task nuisance variables. We demonstrate that max-su
m inference in the DRMM yields an algorithm that exactly reproduces the operations in deep convolutional neural networks (DCNs), providing a first principles derivation. Our framework provides new insights into the successes and shortcomings of DCNs as well as a principled route to their improvement. DRMM training via the Expectation-Maximization (EM) algorithm is a powerful alternative to DCN back-propagation, and initial training results are promising. Classification based on the DRMM and other variants outperforms DCNs in supervised digit classification, training 2-3x faster while achieving similar accuracy. Moreover, the DRMM is applicable to semi-supervised and unsupervised learning tasks, achieving results that are state-of-the-art in several categories on the MNIST benchmark and comparable to state of the art on the CIFAR10 benchmark.
الأسئلة المقترحة
سجل دخول لتتمكن من نشر تعليقات
التعليقات
جاري جلب التعليقات
سجل دخول لتتمكن من متابعة معايير البحث التي قمت باختيارها
