arXiv research

Generates samples conditioned on labels using optimal transport.

In many real-world classification problems, the labels of training examples are randomly corrupted. Most previous theoretical work on classification with label noise assumes that the two classes are separable, that the label noise is independent of the true class label, or that the noise proportions for each class are …

Unified view of label shift estimation methods.

LACD uses unlabeled data to improve conditional diffusion models.

A new method compresses conditional distributions of labelled data.

Majority of state-of-the-art deep learning methods are discriminative approaches, which model the conditional distribution of labels given inputs features. The success of such approaches heavily depends on high-quality labeled instances, which are not easy to obtain, especially as the number of candidate classes increa…

S2cGAN uses fewer labels to train cGANs effectively.

CAN learns conditional and interventional distributions from unlabeled data.

EnMDAP aligns conditional distributions for multi-source domain adaptation using pseudolabels.

Paper proposes a new method to aggregate multiple sources with different label distributions.

New CPS model tackles conditional probability shift in machine learning.

Estimates calibration error under label shift without labels.

New approach improves domain adaptation with label shift assumptions.

We introduce a new model for building conditional generative models in a semi-supervised setting to conditionally generate data given attributes by adapting the GAN framework. The proposed semi-supervised GAN (SS-GAN) model uses a pair of stacked discriminators to learn the marginal distribution of the data, and the co…

We study the problem of learning conditional generators from noisy labeled samples, where the labels are corrupted by random noise. A standard training of conditional GANs will not only produce samples with wrong labels, but also generate poor quality samples. We consider two scenarios, depending on whether the noise m…

We propose an adversarial training procedure for learning a causal implicit generative model for a given causal graph. We show that adversarial training can be used to learn a generative model with true observational and interventional distributions if the generator architecture is consistent with the given causal grap…

New method removes pseudo-label bias for unsupervised domain adaptation.

Optimal transport aligns source and target distributions for domain adaptation.

SJS model predicts label shifts in multinomial datasets.

Study approximates operators on labelled conditional distributions for non-exchangeable systems.

Study reveals differences in label shift problem difficulty in supervised vs. unsupervised settings.

Generative adversarial networks (GANs) are a framework that learns a generative distribution through adversarial training. Recently, their class-conditional extensions (e.g., conditional GAN (cGAN) and auxiliary classifier GAN (AC-GAN)) have attracted much attention owing to their ability to learn the disentangled repr…

CcGAN tackles conditional image generation for continuous labels.

RLSbench benchmarks domain adaptation under label proportion shifts, revealing widespread failures and proposing a two-step meta-algorithm.

Proposes a new approach to MSDA by introducing latent covariate shift to handle varying label distributions.

Classifier chains are popular and effective method to tackle a multi-label classification problem. The aim of this paper is to study the asymptotic properties of the chain model in which the conditional probabilities are of the logistic form. In particular we find conditions on the number of labels and the distribution…

Efficient algorithm for halfspaces with specific noise conditions.

This paper introduces LR-FFS for robust feature screening in federated learning under label shift.

Paper proposes SJS model to estimate model performance under covariate and label shifts.

New method MRI improves machine learning models' ability to generalize to unseen data.

Transfer learning aims to improve learning in target domain by borrowing knowledge from a related but different source domain. To reduce the distribution shift between source and target domains, recent methods have focused on exploring invariant representations that have similar distributions across domains. However, w…

Paper investigates methods to improve classification by inducing a hierarchy from flat labels.

We present a new replay-based method of continual classification learning that we term "conditional replay" which generates samples and labels together by sampling from a distribution conditioned on the class. We compare conditional replay to another replay-based continual learning paradigm (which we term "marginal rep…

Deep models can fit noisy labels, but robustness and reliability are still issues.

Detects changes in classifier scores to identify shifts in class priors.

This paper proposes a semi-conditional normalizing flow model for semi-supervised learning. The model uses both labelled and unlabeled data to learn an explicit model of joint distribution over objects and labels. Semi-conditional architecture of the model allows us to efficiently compute a value and gradients of the m…

NURD improves model performance by distilling representations independent of nuisance variables.

Ridge regression shows different behaviors in binary classification with noisy labels.

Deep generative models are becoming a cornerstone of modern machine learning. Recent work on conditional generative adversarial networks has shown that learning complex, high-dimensional distributions over natural images is within reach. While the latest models are able to generate high-fidelity, diverse natural images…

The paper introduces localized conformal p-values for conditional testing problems.

Well-known for its simplicity and effectiveness in classification, AdaBoost, however, suffers from overfitting when class-conditional distributions have significant overlap. Moreover, it is very sensitive to noise that appears in the labels. This article tackles the above limitations simultaneously via optimizing a mod…

Under covariate shift, training (source) data and testing (target) data differ in input space distribution, but share the same conditional label distribution. This poses a challenging machine learning task. Robust Bias-Aware (RBA) prediction provides the conditional label distribution that is robust to the worstcase lo…

We propose a novel nonparametric online predictor for discrete labels conditioned on multivariate continuous features. The predictor is based on a feature space discretization induced by a full-fledged k-d tree with randomly picked directions and a recursive Bayesian distribution, which allows to automatically learn th…

CWAN tackles multi-source heterogeneous domain adaptation with conditional weighting.

Corrects distribution shift in target shift scenarios using importance weighting.

SIG model identifies invariant variables for MSDA with fewer domain constraints.

ELSA efficiently adapts to label shift without post-prediction calibrations.

Transductive Adversarial Networks (TAN) is a novel domain-adaptation machine learning framework that is designed for learning a conditional probability distribution on unlabelled input data in a target domain, while also only having access to: (1) easily obtained labelled data from a related source domain, which may ha…