Search Results for author:
Found 8 papers, 4 papers with code
Enriching Disentanglement: Definitions to Metrics
Disentangled representation learning is a challenging task that involves separating multiple factors of variation in complex data.
A Category-theoretical Meta-analysis of Definitions of Disentanglement
Disentangling the factors of variation in data is a fundamental concept in machine learning and has been studied in various ways by different researchers, leading to a multitude of definitions.
Equivariant Disentangled Transformation for Domain Generalization under Combination Shift
To formally analyze this issue, we provide a unique algebraic formulation of the combination shift problem based on the concepts of homomorphism, equivariance, and a refined definition of disentanglement.
Approximating Instance-Dependent Noise via Instance-Confidence Embedding
Label noise in multiclass classification is a major obstacle to the deployment of learning systems.
Learning Noise Transition Matrix from Only Noisy Labels via Total Variation Regularization
To estimate the transition matrix from noisy data, existing methods often need to estimate the noisy class-posterior, which could be unreliable due to the overconfidence of neural networks.
Classification with Rejection Based on Cost-sensitive Classification
The goal of classification with rejection is to avoid risky misclassification in error-critical applications such as medical diagnosis and product inspection.
Learning from Aggregate Observations
We study the problem of learning from aggregate observations where supervision signals are given to sets of instances instead of individual instances, while the goal is still to predict labels of unseen individuals.
Learning from Indirect Observations
Weakly-supervised learning is a paradigm for alleviating the scarcity of labeled data by leveraging lower-quality but larger-scale supervision signals.
