Ieee Transactions on Knowledge and Data Engineering 1 Training Cost-sensitive Neural Networks with Methods Addressing the Class Imbalance Problem

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Citations in the corpus

Uncovering and Mitigating Algorithmic Bias through Learned Latent Structure (2019, neutral): “Resampling for class imbalance: Resampling approaches have largely focused on addressing class imbalances (More 2016; Zhou and Liu 2006), as opposed to biases within individual classes.”
A systematic study of the class imbalance problem in convolutional neural networks (2017, methodology): “In such case, the learning algorithms are modiﬁed, e.g. by introducing diﬀerent weights to misclassiﬁcation of examples from diﬀerent classes [22] or explicitly adjusting prior class probabilities [23].”
Automatically Neutralizing Subjective Bias in Text (2019, neutral): “This loss function is related to previous work on grammar correction (Junczys-Dowmunt et al. 2018), and cost-sensitive learning (Zhou and Liu 2006).”
Variational Autoencoder for End-to-End Control of Autonomous Driving with Novelty Detection and Training De-biasing (2018, background): “When the classes are explicitly defined and labeled it is possible to resample the dataset [26], [27] or even reweight the loss function [28], [29] to avoid training bias.”
A supervised learning approach for imbalanced data sets (2008, methodology): “The class imbalance problem, which is one of the fundamental problems in machine learning, has received much attention recently [1,4,9, 14, 15].”
Deep Imbalanced Learning for Face Recognition and Attribute Prediction (2018, background): “Liu et al. [37] proposed to maximize the hyperspherical margin regardless of class imbalance, while Wang et al. [29] proposed a metalearning approach that transfers model parameters from the majority to minority class.”
Training and assessing classification rules with imbalanced data (2012, unknown): “It is easy to show that, given that c j is the cost of misclassifying a class Y j object, the minimum loss is achieved by assigning an observation to the class Examples of this approach can be found in Eitrich et al. (2007) as well as in Zhou and Liu (2006).”
Learning from Imbalanced Data (2009, background): “However, we note that a more significant performance increase can be achieved by applying this estimate to ensemble methods by using cross-validation techniques on a given set; a similar approach is considered in [11], however using a slightly different estimate.”
Multiclass Imbalance Problems: Analysis and Potential Solutions (2012, background): “They have been shown to be less effective or even cause a negative effect in dealing with multiclass tasks [9].”
Using Class Imbalance Learning for Software Defect Prediction (2013, background): “Threshold-moving is also considered in our study as a frequently used cost-sensitive technique [21].”
Classification with class imbalance problem: A review (2015, methodology): “A recent work from [86] proposed for a SVM with Asymmetrical Misclassifications Cost whereas like [107] which use neural network to train on cost-sensitive classification.”
Learning Deep Representation for Imbalanced Classification (2016, background): “To counter the negative effects, one often chooses from a few available options, which have been extensively studied in the past [7, 9, 11, 17, 18, 30, 40, 41, 46, 48].”