English
Related papers

Related papers: Omitted Labels Induce Nontransitive Paradoxes in C…

200 papers

Recent advancements in unsupervised domain adaptation (UDA) and semi-supervised learning (SSL), particularly incorporating causality, have led to significant methodological improvements in these learning problems. However, a formal theory…

Machine Learning · Computer Science 2024-09-17 Xuetong Wu , Mingming Gong , Jonathan H. Manton , Uwe Aickelin , Jingge Zhu

Many classification problems can be difficult to formulate directly in terms of the traditional supervised setting, where both training and test samples are individual feature vectors. There are cases in which samples are better described…

Machine Learning · Statistics 2016-07-12 Veronika Cheplygina , David M. J. Tax , Marco Loog

While deep learning has revolutionized financial forecasting through sophisticated architectures, the design of the supervision signal itself is rarely scrutinized. We challenge the canonical assumption that training labels must strictly…

Machine Learning · Computer Science 2026-02-12 Chen-Hui Song , Shuoling Liu , Liyuan Chen

With increasing applications of semantic segmentation, numerous datasets have been proposed in the past few years. Yet labeling remains expensive, thus, it is desirable to jointly train models across aggregations of datasets to enhance data…

Computer Vision and Pattern Recognition · Computer Science 2022-03-01 Dongwan Kim , Yi-Hsuan Tsai , Yumin Suh , Masoud Faraki , Sparsh Garg , Manmohan Chandraker , Bohyung Han

The semantics as to which set of arguments in a given argumentation graph may be acceptable (acceptability semantics) can be characterised in a few different ways. Among them, labelling-based approach allows for concise and flexible…

Artificial Intelligence · Computer Science 2020-07-14 Ryuta Arisaka , Takayuki Ito

Due to the expensive costs of collecting labels in multi-label classification datasets, partially annotated multi-label classification has become an emerging field in computer vision. One baseline approach to this task is to assume…

Computer Vision and Pattern Recognition · Computer Science 2023-04-05 Youngwook Kim , Jae Myung Kim , Jieun Jeong , Cordelia Schmid , Zeynep Akata , Jungwoo Lee

Default logic encounters some conceptual difficulties in representing common sense reasoning tasks. We argue that we should not try to formulate modular default rules that are presumed to work in all or most circumstances. We need to take…

Artificial Intelligence · Computer Science 2013-02-08 Choh Man Teng

In-context learning (ICL) i.e. showing LLMs only a few task-specific demonstrations has led to downstream gains with no task-specific fine-tuning required. However, LLMs are sensitive to the choice of prompts, and therefore a crucial…

Computation and Language · Computer Science 2024-01-31 Lingyu Gao , Aditi Chaudhary , Krishna Srinivasan , Kazuma Hashimoto , Karthik Raman , Michael Bendersky

We propose a manifestly covariant framework for causal set dynamics. The framework is based on a structure, dubbed covtree, which is a partial order on certain sets of finite, unlabeled causal sets. We show that every infinite path in…

General Relativity and Quantum Cosmology · Physics 2020-03-27 Fay Dowker , Nazireen Imambaccus , Amelia Owens , Rafael Sorkin , Stav Zalel

Complex numbers define the relationship between entities in many situations. A canonical example would be the off-diagonal terms in a Hamiltonian matrix in quantum physics. Recent years have seen an increasing interest to extend the tools…

Social and Information Networks · Computer Science 2023-07-06 Yu Tian , Renaud Lambiotte

In addition to reproducing discriminatory relationships in the training data, machine learning systems can also introduce or amplify discriminatory effects. We refer to this as introduced unfairness, and investigate the conditions under…

Machine Learning · Computer Science 2022-02-24 Carolyn Ashurst , Ryan Carey , Silvia Chiappa , Tom Everitt

The presence of label noise often misleads the training of deep neural networks. Departing from the recent literature which largely assumes the label noise rate is only determined by the true label class, the errors in human-annotated…

Machine Learning · Computer Science 2021-03-31 Zhaowei Zhu , Tongliang Liu , Yang Liu

Motifs often recur in musical works in altered forms, preserving aspects of their identity while undergoing local variation. This paper investigates how such motivic transformations occur within their musical context in symbolic music. To…

Sound · Computer Science 2026-03-30 Ron Taieb , Yoel Greenberg , Barak Sober

The paper analyzes the problem of judgments or preferences subsequent to initial analysis by autonomous agents in a hierarchical system where the higher level agents does not have access to group size information. We propose methods that…

Artificial Intelligence · Computer Science 2018-02-13 Subhash Kak

Shortcut learning, in which models make use of easy-to-represent but unstable associations, is a major failure mode for robust machine learning. We study a flexible, causally-motivated approach to training robust predictors by discouraging…

Machine Learning · Computer Science 2022-02-24 Maggie Makar , Ben Packer , Dan Moldovan , Davis Blalock , Yoni Halpern , Alexander D'Amour

Fairness is increasingly recognized as a critical component of machine learning systems. However, it is the underlying data on which these systems are trained that often reflect discrimination, suggesting a database repair problem. Existing…

Databases · Computer Science 2019-10-04 Babak Salimi , Luke Rodriguez , Bill Howe , Dan Suciu

This paper investigates how global decision problems over arithmetically represented domains acquire reflective structure through class-quantification. Arithmetization forces diagonal fixed points whose verification requires reflection…

Computational Complexity · Computer Science 2025-11-19 Milan Rosko

Interpretability research takes counterfactual theories of causality for granted. Most causal methods rely on counterfactual interventions to inputs or the activations of particular model components, followed by observations of the change…

Machine Learning · Computer Science 2024-07-08 Aaron Mueller

Partial-label learning is a kind of weakly-supervised learning with inexact labels, where for each training example, we are given a set of candidate labels instead of only one true label. Recently, various approaches on partial-label…

Machine Learning · Computer Science 2022-08-30 Zhenguo Wu , Jiaqi Lv , Masashi Sugiyama

The problem of domain generalization concerns learning predictive models that are robust to distribution shifts when deployed in new, previously unseen environments. Existing methods typically require labeled data from multiple training…

‹ Prev 1 8 9 10 Next ›