Related papers: Active learning strategies for atomic cluster expa…

Visual action planning particularly excels in applications where the state of the system cannot be computed explicitly, such as manipulation of deformable objects, as it enables planning directly from raw images. Even though the field has…

Machine learning methods have nowadays become easy-to-use tools for constructing high-dimensional interatomic potentials with ab initio accuracy. Although machine learned interatomic potentials are generally orders of magnitude faster than…

Inspired by the problem of improving classification accuracy on rare or hard subsets of a population, there has been recent interest in models of learning where the goal is to generalize to a collection of distributions, each representing a…

Modeling distributions of covariates, or density estimation, is a core challenge in unsupervised learning. However, the majority of work only considers the joint distribution, which has limited utility in practical situations. A more…

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…

Deep learning models such as Convolutional Neural Networks (CNNs) have demonstrated high levels of effectiveness in a variety of domains, including computer vision and more recently, computational biology. However, training effective models…

Active Learning (AL) addresses the crucial challenge of enabling machines to efficiently gather labeled examples through strategic queries. Among the many AL strategies, Uncertainty Sampling (US) stands out as one of the most widely…

Estimating how individual input variables affect the output of a black-box model is a central task in explainable machine learning. However, existing methods suffer from two key limitations: sensitivity to out-of-distribution (OOD)…

Due to the notorious modality imbalance problem, multimodal learning (MML) leads to the phenomenon of optimization imbalance, thus struggling to achieve satisfactory performance. Recently, some representative methods have been proposed to…

In complex tasks, such as those with large combinatorial action spaces, random exploration may be too inefficient to achieve meaningful learning progress. In this work, we use a curriculum of progressively growing action spaces to…

Gathering labeled data to train well-performing machine learning models is one of the critical challenges in many applications. Active learning aims at reducing the labeling costs by an efficient and effective allocation of costly labeling…

Deep ensembles perform better than a single network thanks to the diversity among their members. Recent approaches regularize predictions to increase diversity; however, they also drastically decrease individual members' performances. In…

Active learning (AL) is a prominent technique for reducing the annotation effort required for training machine learning models. Deep learning offers a solution for several essential obstacles to deploying AL in practice but introduces many…

Active Learning is a very common yet powerful framework for iteratively and adaptively sampling subsets of the unlabeled sets with a human in the loop with the goal of achieving labeling efficiency. Most real world datasets have imbalance…

The discovery of new energetic materials is critical for advancing technologies from defense to private industry. However, experimental approaches remain slow and expensive while computational alternatives require accurate material property…

Neural ordinary differential equations (NODEs) presented a new paradigm to construct (continuous-time) neural networks. While showing several good characteristics in terms of the number of parameters and the flexibility in constructing…

In recent years, the creation of block-structured dictionary has attracted a lot of interest. Learning such dictionaries involve two step process: block formation and dictionary update. Both these steps are important in producing an…

Cold-start active learning (CSAL) selects valuable instances from an unlabeled dataset for manual annotation. It provides high-quality data at a low annotation cost for label-scarce text classification. However, existing CSAL methods…

Active learning is a machine learning paradigm that aims to improve the performance of a model by strategically selecting and querying unlabeled data. One effective selection strategy is to base it on the model's predictive uncertainty,…

To identify a stationary action profile for a population of competitive agents, each executing private strategies, we introduce a novel active-learning scheme where a centralized external observer (or entity) can probe the agents' reactions…