Related papers: Efficient Uncertainty Tracking for Complex Queries…
AI-Powered database (AI-DB) is a novel relational database system that uses a self-supervised neural network, database embedding, to enable semantic SQL queries on relational tables. In this paper, we describe an architecture and…
Quantifying uncertainty and updating reliability are essential for ensuring the safety and performance of engineering systems. This study develops a hierarchical Bayesian modeling (HBM) framework to quantify uncertainty and update…
In this paper, we propose a novel, effective and efficient probabilistic pruning criterion for probabilistic similarity queries on uncertain data. Our approach supports a general uncertainty model using continuous probabilistic density…
Deep learning-based surrogate models have demonstrated remarkable advantages over classical solvers in terms of speed, often achieving speedups of 10 to 1000 times over traditional partial differential equation (PDE) solvers. However, a…
Approximate Bayesian computation (ABC) is one of the most popular "likelihood-free" methods. These methods have been applied in a wide range of fields by providing solutions to intractable likelihood problems in which exact Bayesian…
Unsupervised Domain Adaptive (UDA) object re-identification (Re-ID) aims at adapting a model trained on a labeled source domain to an unlabeled target domain. State-of-the-art object Re-ID approaches adopt clustering algorithms to generate…
Uncertainty quantification (UQ) methods for Large Language Models (LLMs) encompass a variety of approaches, with two major types being particularly prominent: information-based, which focus on model confidence expressed as token…
Collecting annotations from multiple independent sources could mitigate the impact of potential noises and biases from a single source, which is a common practice in medical image segmentation. Learning segmentation networks from…
Audit transaction testing validates accuracy and completeness of customer-facing statements against internal systems of record. Traditional manual, sample-based review of unstructured PDF statements is labor-intensive and does not scale to…
In modern databases, the practice of data normalization continues to be important in improving data integrity, minimizing redundancies, and eliminating anomalies. However, since its inception and consequent improvements, there have been no…
Neural networks (NNs) are currently changing the computational paradigm on how to combine data with mathematical laws in physics and engineering in a profound way, tackling challenging inverse and ill-posed problems not solvable with…
Uncertainty estimation is an essential and heavily-studied component for the reliable application of semantic segmentation methods. While various studies exist claiming methodological advances on the one hand, and successful application on…
Named Entity Recognition (NER) serves as a foundational component in many natural language processing (NLP) pipelines. However, current NER models typically output a single predicted label sequence without any accompanying measure of…
The knowledge that humans hold about a problem often extends far beyond a set of training data and output labels. While the success of deep learning mostly relies on supervised training, important properties cannot be inferred efficiently…
When does a large language model (LLM) know what it does not know? Uncertainty quantification (UQ) provides measures of uncertainty, such as an estimate of the confidence in an LLM's generated output, and is therefore increasingly…
Human annotations are vital to supervised learning, yet annotators often disagree on the correct label, especially as annotation tasks increase in complexity. A strategy to improve label quality is to ask multiple annotators to label the…
We propose a computationally efficient method to construct nonparametric, heteroscedastic prediction bands for uncertainty quantification, with or without any user-specified predictive model. Our approach provides an alternative to the…
Universal domain adaptation (UniDA) is a general unsupervised domain adaptation setting, which addresses both domain and label shifts in adaptation. Its main challenge lies in how to identify target samples in unshared or unknown classes.…
As machine learning (ML) models are increasingly deployed in high-stakes domains, trustworthy uncertainty quantification (UQ) is critical for ensuring the safety and reliability of these models. Traditional UQ methods rely on specifying a…
Text-based person search faces inherent limitations due to data scarcity, driven by stringent privacy constraints and the high cost of manual annotation. To mitigate this, existing methods usually rely on a Pretrain-then-Finetune paradigm,…