Related papers: Rectifying Mono-Label Boolean Classifiers

Label noise, which refers to the mislabeling of instances in a dataset, can significantly impair classifier performance, increase model complexity, and affect feature selection. While most research has concentrated on deep neural networks…

Statistically consistent methods based on the noise transition matrix ($T$) offer a theoretically grounded solution to Learning with Noisy Labels (LNL), with guarantees of convergence to the optimal clean-data classifier. In practice,…

We present a Rocq library for monoidal categories, which includes a decision procedure for proving equality of morphisms as well as notations that make it possible to reason as if they were strict, inferring MacLane isomorphims…

Learning multi-label image recognition with incomplete annotation is gaining popularity due to its superior performance and significant labor savings when compared to training with fully labeled datasets. Existing literature mainly focuses…

Regularization is essential for avoiding over-fitting to training data in network optimization, leading to better generalization of the trained networks. The label noise provides a strong implicit regularization by replacing the target…

Designing objective functions robust to label noise is crucial for real-world classification algorithms. In this paper, we investigate the robustness to label noise of an $f$-divergence-based class of objective functions recently proposed…

Machine learning classifiers often produce probabilistic predictions that are critical for accurate and interpretable decision-making in various domains. The quality of these predictions is generally evaluated with proper losses, such as…

Unsupervised object re-identification targets at learning discriminative representations for object retrieval without any annotations. Clustering-based methods conduct training with the generated pseudo labels and currently dominate this…

We present a comprehensive programme analysing the decomposition of proof systems for non-classical logics into proof systems for other logics, especially classical logic, using an algebra of constraints. That is, one recovers a proof…

Noisy multi-label learning has garnered increasing attention due to the challenges posed by collecting large-scale accurate labels, making noisy labels a more practical alternative. Motivated by noisy multi-class learning, the introduction…

We calculate the moduli dependent part of string one-loop threshold corrections to gauge couplings for the heterotic string theory compactified on abelian toroidal orbifolds, allowing for arbitrary discrete Wilson lines. We show that the…

Commit Classification (CC) is an important task in software maintenance, which helps software developers classify code changes into different types according to their nature and purpose. It allows developers to understand better how their…

We consider learning to optimize a classification metric defined by a black-box function of the confusion matrix. Such black-box learning settings are ubiquitous, for example, when the learner only has query access to the metric of…

Text classification in education, usually called auto-tagging, is the automated process of assigning relevant tags to educational content, such as questions and textbooks. However, auto-tagging suffers from a data scarcity problem, which…

We develop a new symbolic-numeric algorithm for the certification of singular isolated points, using their associated local ring structure and certified numerical computations. An improvement of an existing method to compute inverse systems…

We consider a variant of online binary classification where a learner sequentially assigns labels ($0$ or $1$) to items with unknown true class. If, but only if, the learner chooses label $1$ they immediately observe the true label of the…

In multi-label classification, each example in a dataset may be annotated as belonging to one or more classes (or none of the classes). Example applications include image (or document) tagging where each possible tag either applies to a…

In multiclass classification, the goal is to learn how to predict a random label $Y$, valued in $\mathcal{Y}=\{1,\; \ldots,\; K \}$ with $K\geq 3$, based upon observing a r.v. $X$, taking its values in $\mathbb{R}^q$ with $q\geq 1$ say, by…

Automated decision support systems promise to help human experts solve multiclass classification tasks more efficiently and accurately. However, existing systems typically require experts to understand when to cede agency to the system or…

Complementary-label learning (CLL) is a weakly supervised paradigm where instances are labeled with classes they do not belong to. Despite a decade of research, CLL methods remain competitive mainly on 10-class classification, with scaling…