Variational Imbalanced Regression

by   Ziyan Wang, et al.
Georgia Institute of Technology
Rutgers University

Existing regression models tend to fall short in both accuracy and uncertainty estimation when the label distribution is imbalanced. In this paper, we propose a probabilistic deep learning model, dubbed variational imbalanced regression (VIR), which not only performs well in imbalanced regression but naturally produces reasonable uncertainty estimation as a byproduct. Different from typical variational autoencoders assuming I.I.D. representations (a data point's representation is not directly affected by other data points), our VIR borrows data with similar regression labels to compute the latent representation's variational distribution; furthermore, different from deterministic regression models producing point estimates, VIR predicts the entire normal-inverse-gamma distributions and modulates the associated conjugate distributions to impose probabilistic reweighting on the imbalanced data, thereby providing better uncertainty estimation. Experiments in several real-world datasets show that our VIR can outperform state-of-the-art imbalanced regression models in terms of both accuracy and uncertainty estimation.


page 1

page 2

page 3

page 4


Delving into Deep Imbalanced Regression

Real-world data often exhibit imbalanced distributions, where certain ta...

A step towards understanding why classification helps regression

A number of computer vision deep regression approaches report improved r...

Mixture of Experts with Uncertainty Voting for Imbalanced Deep Regression Problems

Data imbalance is ubiquitous when applying machine learning to real-worl...

Variational Hierarchical Mixtures for Learning Probabilistic Inverse Dynamics

Well-calibrated probabilistic regression models are a crucial learning c...

Heteroskedastic and Imbalanced Deep Learning with Adaptive Regularization

Real-world large-scale datasets are heteroskedastic and imbalanced – lab...

OCCER- One-Class Classification by Ensembles of Regression models

One-class classification (OCC) deals with the classification problem in ...

Phase-type distributions for claim severity regression modeling

This paper addresses the task of modeling severity losses using segmenta...

Please sign up or login with your details

Forgot password? Click here to reset