Search Results for author:
Found 11 papers, 8 papers with code
Towards More Accurate Uncertainty Estimation In Text Classification
The uncertainty measurement of classified results is especially important in areas requiring limited human resources for higher accuracy.
Uncertainty-Aware Cross-Lingual Transfer with Pseudo Partial Labels
Large-scale multilingual pre-trained language models have achieved remarkable performance in zero-shot cross-lingual tasks.
TART: Improved Few-shot Text Classification Using Task-Adaptive Reference Transformation
Meta-learning has emerged as a trending technique to tackle few-shot text classification and achieve state-of-the-art performance.
Memetic algorithms for Spatial Partitioning problems
However, the search operators employed by these population-based methods are mostly designed for real-parameter continuous optimization problems.
Sampling-based techniques for designing school boundaries
Motivated by these recent developments, we develop a set of similar sampling techniques for designing school boundaries based on the flip proposal.
Automated Urban Planning for Reimagining City Configuration via Adversarial Learning: Quantification, Generation, and Evaluation
However, three major challenges arise: 1) how to define a quantitative land-use configuration?
Deep diffusion-based forecasting of COVID-19 by incorporating network-level mobility information
The Gaussian Mixture Model layer is implemented to consider the multimodal nature of the real-time data while learning from multiple related time series.
Bridging the Gap between Spatial and Spectral Domains: A Unified Framework for Graph Neural Networks
Deep learning's performance has been extensively recognized recently.
Few-Shot Semantic Segmentation Augmented with Image-Level Weak Annotations
Despite the great progress made by deep neural networks in the semantic segmentation task, traditional neural-networkbased methods typically suffer from a shortage of large amounts of pixel-level annotations.
Bridging the Gap between Spatial and Spectral Domains: A Survey on Graph Neural Networks
Deep learning's success has been widely recognized in a variety of machine learning tasks, including image classification, audio recognition, and natural language processing.
Mitigating Uncertainty in Document Classification
The uncertainty measurement of classifiers' predictions is especially important in applications such as medical diagnoses that need to ensure limited human resources can focus on the most uncertain predictions returned by machine learning models.
