Related papers: Let Experts Feel Uncertainty: A Multi-Expert Label…

Unsupervised domain adaptation methods seek to generalize effectively on unlabeled test data, especially when encountering the common challenge in time series data that distribution shifts occur between training and testing datasets. In…

Recent research has shown that large language models (LLMs) can be effectively used for real-world time series forecasting due to their strong natural language understanding capabilities. However, aligning time series into semantic spaces…

Supervised machine learning often requires human-annotated data. While annotator disagreement is typically interpreted as evidence of noise, population-level label distribution learning (PLDL) treats the collection of annotations for each…

Label distribution learning (LDL) is an interpretable and general learning paradigm that has been applied in many real-world applications. In contrast to the simple logical vector in single-label learning (SLL) and multi-label learning…

Although \textbf{L}abel \textbf{D}istribution \textbf{L}earning (LDL) has promising representation capabilities for characterizing the polysemy of an instance, the complexity and high cost of the label distribution annotation lead to…

The time series classification literature has expanded rapidly over the last decade, with many new classification approaches published each year. Prior research has mostly focused on improving the accuracy and efficiency of classifiers,…

Probabilistic forecasting is not only a way to add more information to a prediction of the future, but it also builds on weaknesses in point prediction. Sudden changes in a time series can still be captured by a cumulative distribution…

Time series forecasting, which aims to predict future values based on historical data, has garnered significant attention due to its broad range of applications. However, real-world time series often exhibit complex non-uniform distribution…

Technological and computational advances continuously drive forward the broad field of deep learning. In recent years, the derivation of quantities describing theuncertainty in the prediction - which naturally accompanies the modeling…

Weather forecasting remains a crucial yet challenging domain, where recently developed models based on deep learning (DL) have approached the performance of traditional numerical weather prediction (NWP) models. However, these DL models,…

Deep learning is increasingly being applied in safety-critical domains. For these scenarios it is important to know the level of uncertainty in a model's prediction to ensure appropriate decisions are made by the system. Deep ensembles are…

Accurate prediction of nonstationary multivariate time series remains a critical challenge in complex industrial systems such as iron ore sintering. In practice, pronounced concept drift compounded by significant label verification latency…

The Mixture-of-Experts (MoE) architecture has enabled the creation of massive yet efficient Large Language Models (LLMs). However, the standard deterministic routing mechanism presents a significant limitation: its inherent brittleness is a…

Large Language Models (LLMs) often exhibit misalignment between the quality of their generated responses and the confidence estimates they assign to them. Bayesian treatments, such as marginalizing over a reliable weight posterior or over…

Sequential labeling is a task predicting labels for each token in a sequence, such as Named Entity Recognition (NER). NER tasks aim to extract entities and predict their labels given a text, which is important in information extraction.…

In multi-task learning, labels are often missing irregularly across samples, which can be fully labeled, partially labeled or unlabeled. The irregular label presence often appears in scientific studies due to experimental limitations. It…

Computer-aided diagnosis systems must make critical decisions from medical images that are often noisy, ambiguous, or conflicting, yet today's models are trained on overly simplistic labels that ignore diagnostic uncertainty. One-hot labels…

Label Distribution Learning (LDL) is a novel machine learning paradigm that assigns label distribution to each instance. Many LDL methods proposed to leverage label correlation in the learning process to solve the exponential-sized output…

We present a novel framework that can combine multi-domain learning (MDL), data imputation (DI) and multi-task learning (MTL) to improve performance for classification and regression tasks in different domains. The core of our method is an…

Machine learning practitioners often face significant challenges in formally integrating their prior knowledge and beliefs into predictive models, limiting the potential for nuanced and context-aware analyses. Moreover, the expertise needed…