Search Results for author:
Found 20 papers, 11 papers with code
Dissecting Sample Hardness: A Fine-Grained Analysis of Hardness Characterization Methods for Data-Centric AI
Additionally, we propose the Hardness Characterization Analysis Toolkit (H-CAT), which supports comprehensive and quantitative benchmarking of HCMs across the hardness taxonomy and can easily be extended to new HCMs, hardness types, and datasets.
DAGnosis: Localized Identification of Data Inconsistencies using Structures
Identification and appropriate handling of inconsistencies in data at deployment time is crucial to reliably use machine learning models.
Large Language Models to Enhance Bayesian Optimization
Bayesian optimization (BO) is a powerful approach for optimizing complex and expensive-to-evaluate black-box functions.
Curated LLM: Synergy of LLMs and Data Curation for tabular augmentation in ultra low-data regimes
Machine Learning (ML) in low-data settings remains an underappreciated yet crucial problem.
When is Off-Policy Evaluation Useful? A Data-Centric Perspective
On the one hand, it brings opportunities for safe policy improvement under high-stakes scenarios like clinical guidelines.
TRIAGE: Characterizing and auditing training data for improved regression
Data quality is crucial for robust machine learning algorithms, with the recent interest in data-centric AI emphasizing the importance of training data characterization.
Reimagining Synthetic Tabular Data Generation through Data-Centric AI: A Comprehensive Benchmark
In an empirical study, we evaluate the performance of five state-of-the-art models for tabular data generation on eleven distinct tabular datasets.
U-PASS: an Uncertainty-guided deep learning Pipeline for Automated Sleep Staging
As machine learning becomes increasingly prevalent in critical fields such as healthcare, ensuring the safety and reliability of machine learning systems becomes paramount.
Improving Adaptive Conformal Prediction Using Self-Supervised Learning
However, the use of self-supervision beyond model pretraining and representation learning has been largely unexplored.
DC-Check: A Data-Centric AI checklist to guide the development of reliable machine learning systems
However, this remains a nascent area with no standardized framework to guide practitioners to the necessary data-centric considerations or to communicate the design of data-centric driven ML systems.
Data-IQ: Characterizing subgroups with heterogeneous outcomes in tabular data
High model performance, on average, can hide that models may systematically underperform on subgroups of the data.
What is Flagged in Uncertainty Quantification? Latent Density Models for Uncertainty Categorization
Uncertainty Quantification (UQ) is essential for creating trustworthy machine learning models.
Continuous-Time Modeling of Counterfactual Outcomes Using Neural Controlled Differential Equations
To assess solutions to this problem, we propose a controllable simulation environment based on a model of tumor growth for a range of scenarios with irregular sampling reflective of a variety of clinical scenarios.
Differentiable and Transportable Structure Learning
Directed acyclic graphs (DAGs) encode a lot of information about a particular distribution in their structure.
Modeling Disagreement in Automatic Data Labelling for Semi-Supervised Learning in Clinical Natural Language Processing
Computational models providing accurate estimates of their uncertainty are crucial for risk management associated with decision making in healthcare contexts.
Data-SUITE: Data-centric identification of in-distribution incongruous examples
These estimators can be used to evaluate the congruence of test instances with respect to the training set, to answer two practically useful questions: (1) which test instances will be reliably predicted by a model trained with the training instances?
MCU-Net: A framework towards uncertainty representations for decision support system patient referrals in healthcare contexts
Incorporating a human-in-the-loop system when deploying automated decision support is critical in healthcare contexts to create trust, as well as provide reliable performance on a patient-to-patient basis.
Machine learning discrimination of Parkinson's Disease stages from walker-mounted sensors data
A large set of features, some unique to this study are extracted and three feature selection methods are compared using a multi-class Random Forest (RF) classifier.
Automated machine vision enabled detection of movement disorders from hand drawn spirals
The discrimination accuracy of PD from controls was 98. 2%.
Towards calibrated and scalable uncertainty representations for neural networks
For many applications it is critical to know the uncertainty of a neural network's predictions.
