Search Results for author:
Found 20 papers, 10 papers with code
TAXI: Evaluating Categorical Knowledge Editing for Language Models
We then use TAXI to evaluate popular editors' consistency, measuring how often editing a subject's category appropriately edits its properties.
UniTS: Building a Unified Time Series Model
However, current foundation models apply to sequence data but not to time series, which present unique challenges due to the inherent diverse and multidomain time series datasets, diverging task specifications across forecasting, classification and other types of tasks, and the apparent need for task-specialized models.
MATHWELL: Generating Age-Appropriate Educational Math Word Problems
MATHWELL's performance despite being trained by finetuning only highlights the quality of our synthetic data for training age-appropriate word problem generators.
Improving Black-box Robustness with In-Context Rewriting
Most techniques for improving OOD robustness are not applicable to settings where the model is effectively a black box, such as when the weights are frozen, retraining is costly, or the model is leveraged via an API.
Learning from Time Series under Temporal Label Noise
We first demonstrate the importance of modelling the temporal nature of the label noise function and how existing methods will consistently underperform.
Machine Learning for Health symposium 2023 -- Findings track
A collection of the accepted Findings papers that were presented at the 3rd Machine Learning for Health symposium (ML4H 2023), which was held on December 10, 2023, in New Orleans, Louisiana, USA.
Multi-State Brain Network Discovery
We refer to such brain networks as multi-state, and this mixture can help us understand human behavior.
Continuous Time Evidential Distributions for Irregular Time Series
Prevalent in many real-world settings such as healthcare, irregular time series are challenging to formulate predictions from.
Interpretable Unified Language Checking
Despite recent concerns about undesirable behaviors generated by large language models (LLMs), including non-factual, biased, and hateful language, we find LLMs are inherent multi-task language checkers based on their latent representations of natural and social knowledge.
Finding Short Signals in Long Irregular Time Series with Continuous-Time Attention Policy Networks
Using this insight, we then propose CAT, a model that classifies multivariate ITS by explicitly seeking highly-relevant portions of an input series' timeline.
Aging with GRACE: Lifelong Model Editing with Discrete Key-Value Adaptors
We propose GRACE, a lifelong model editing method, which implements spot-fixes on streaming errors of a deployed model, ensuring minimal impact on unrelated inputs.
Class-Specific Explainability for Deep Time Series Classifiers
Instead, when a classifier is choosing between many classes, an effective explanation must show what sets the chosen class apart from the rest.
Stop&Hop: Early Classification of Irregular Time Series
We bridge this gap and study early classification of irregular time series, a new setting for early classifiers that opens doors to more real-world problems.
TWEET-FID: An Annotated Dataset for Multiple Foodborne Illness Detection Tasks
To accelerate the development of machine learning-based models for foodborne outbreak detection, we thus present TWEET-FID (TWEET-Foodborne Illness Detection), the first publicly available annotated dataset for multiple foodborne illness incident detection tasks.
The Road to Explainability is Paved with Bias: Measuring the Fairness of Explanations
Across two different blackbox model architectures and four popular explainability methods, we find that the approximation quality of explanation models, also known as the fidelity, differs significantly between subgroups.
ToxiGen: A Large-Scale Machine-Generated Dataset for Adversarial and Implicit Hate Speech Detection
To help mitigate these issues, we create ToxiGen, a new large-scale and machine-generated dataset of 274k toxic and benign statements about 13 minority groups.
Deep Positive Unlabeled Learning with a Sequential Bias
In this work, we propose DeepSPU, the first method to address this sequential bias problem.
Human Attention Maps for Text Classification: Do Humans and Neural Networks Focus on the Same Words?
Motivated by human attention, computational attention mechanisms have been designed to help neural networks adjust their focus on specific parts of the input data.
Reducing Computation in Recurrent Networks by Selectively Updating State Neurons
As a result, even for high-dimensional hidden states, all dimensions are updated at each timestep regardless of the recurrent memory cell.
Adaptive-Halting Policy Network for Early Classification
Early classification of time series is the prediction of the class label of a time series before it is observed in its entirety.
