Related papers: Diversity-Aware Batch-Mode Active Learning for Eff…

In reinforcement learning (RL) for robotic manipulation, the Decision Transformer (DT) has emerged as an effective framework for addressing long-horizon tasks. However, DT's performance depends heavily on the coverage of collected…

Evaluation is crucial in Information Retrieval. The development of models, tools and methods has significantly benefited from the availability of reusable test collections formed through a standardized and thoroughly tested methodology,…

Active learning is a promising alternative to alleviate the issue of high annotation cost in the computer vision tasks by consciously selecting more informative samples to label. Active learning for object detection is more challenging and…

Active learning is a powerful method for training machine learning models with limited labeled data. One commonly used technique for active learning is BatchBALD, which uses Bayesian neural networks to find the most informative points to…

Uncertainty Sampling is an Active Learning strategy that aims to improve the data efficiency of machine learning models by iteratively acquiring labels of data points with the highest uncertainty. While it has proven effective for…

We design a new algorithm for batch active learning with deep neural network models. Our algorithm, Batch Active learning by Diverse Gradient Embeddings (BADGE), samples groups of points that are disparate and high-magnitude when…

The widespread availability of off-the-shelf machine learning models poses a challenge: which model, of the many available candidates, should be chosen for a given data analysis task? This question of model selection is traditionally…

Due to the privacy protection or the difficulty of data collection, we cannot observe individual outputs for each instance, but we can observe aggregated outputs that are summed over multiple instances in a set in some real-world…

Annotating the right set of data amongst all available data points is a key challenge in many machine learning applications. Batch active learning is a popular approach to address this, in which batches of unlabeled data points are selected…

Most of the existing learning models, particularly deep neural networks, are reliant on large datasets whose hand-labeling is expensive and time demanding. A current trend is to make the learning of these models frugal and less dependent on…

This study addresses the challenge of accurately identifying multi-task contention types in high-dimensional system environments and proposes a unified contention classification framework that integrates representation transformation,…

Accurate free energy representations are crucial for understanding phase dynamics in materials. We employ a scale-bridging approach to incorporate atomistic information into our free energy model by training a neural network on DFT-informed…

Active learning selects the most informative samples to exploit limited annotation budgets. Existing work follows a cumbersome pipeline that repeats the time-consuming model training and batch data selection multiple times. In this paper,…

The test bench time needed for model-based calibration can be reduced with active learning methods for test design. This paper presents an improved strategy for active output selection. This is the task of learning multiple models in the…

The cost of annotating training data has traditionally been a bottleneck for supervised learning approaches. The problem is further exacerbated when supervised learning is applied to a number of correlated tasks simultaneously since the…

Improving performance in multiple domains is a challenging task, and often requires significant amounts of data to train and test models. Active learning techniques provide a promising solution by enabling models to select the most…

Deep learning-based techniques have proven effective in polyp segmentation tasks when provided with sufficient pixel-wise labeled data. However, the high cost of manual annotation has created a bottleneck for model generalization. To…

Supervised machine learning relies on the availability of good labelled data for model training. Labelled data is acquired by human annotation, which is a cumbersome and costly process, often requiring subject matter experts. Active…

The topic of deep learning has seen a surge of interest in recent years both within and outside of the field of Statistics. Deep models leverage both nonlinearity and interaction effects to provide superior predictions in many cases when…

Leveraging the wealth of unlabeled data produced in recent years provides great potential for improving supervised models. When the cost of acquiring labels is high, probabilistic active learning methods can be used to greedily select the…