Related papers: SynCoTrain: A Dual Classifier PU-learning Framewor…

Synthetic data becomes crucial for large language model training, but its effectiveness is highly inconsistent. We provide an information-theoretic account of this inconsistency: synthetic data improves a model only when the…

Leveraging new data sources is a key step in accelerating the pace of materials design and discovery. To complement the strides in synthesis planning driven by historical, experimental, and computed data, we present an automated method for…

Positive--unlabeled (PU) learning considers two samples, a positive set P with observations from only one class and an unlabeled set U with observations from two classes. The goal is to classify observations in U. Class mixture proportion…

Materials synthesis optimization is constrained by serial feedback processes that rely on manual tools and intuition across multiple siloed modes of characterization. We automate and generalize feature extraction of reflection high-energy…

Structural prediction for the discovery of novel materials is a long sought after goal of computational physics and materials sciences. The success is rather limited for methods such as the simulated annealing method (SA) that require…

In the steel production domain, recycling ferrous scrap is essential for environmental and economic sustainability, as it reduces both energy consumption and greenhouse gas emissions. However, the classification of scrap materials poses a…

Machine learning systems struggle with robustness, under subpopulation shifts. This problem becomes especially pronounced in scenarios where only a subset of attribute combinations is observed during training -a severe form of subpopulation…

The integration of machine learning techniques in materials discovery has become prominent in materials science research and has been accompanied by an increasing trend towards open-source data and tools to propel the field. Despite the…

Positive unlabeled (PU) learning is useful in various practical situations, where there is a need to learn a classifier for a class of interest from an unlabeled data set, which may contain anomalies as well as samples from unknown classes.…

State-of-the-art face recognition networks are often computationally expensive and cannot be used for mobile applications. Training lightweight face recognition models also requires large identity-labeled datasets. Meanwhile, there are…

Synthetic sequence-controlled polymers promise to transform polymer science by combining the chemical versatility of synthetic polymers with the precise sequence-mediated functionality of biological proteins. However, design of these…

In this paper, we develop a novel benchmark suite including both a 2D synthetic image dataset and a 3D synthetic point cloud dataset. Our work is a sub-task in the framework of a remanufacturing project, in which small electric motors are…

While machine learning has emerged in recent years as a useful tool for rapid prediction of materials properties, generating sufficient data to reliably train models without overfitting is still impractical for many applications. Towards…

In this paper, we focus on semi-supervised object detection to boost performance of proposal-based object detectors (a.k.a. two-stage object detectors) by training on both labeled and unlabeled data. However, it is non-trivial to train…

The unsupervised pretraining of object detectors has recently become a key component of object detector training, as it leads to improved performance and faster convergence during the supervised fine-tuning stage. Existing unsupervised…

Deep neural networks (DNNs) have shown their success as high-dimensional function approximators in many applications; however, training DNNs can be challenging in general. DNN training is commonly phrased as a stochastic optimization…

Predicting the future motion of surrounding agents is essential for autonomous vehicles (AVs) to operate safely in dynamic, human-robot-mixed environments. However, the scarcity of large-scale driving datasets has hindered the development…

We propose an approach to materials prediction that uses a machine-learning interatomic potential to approximate quantum-mechanical energies and an active learning algorithm for the automatic selection of an optimal training dataset. Our…

Metamaterials are artificial materials that are designed to meet unseen properties in nature, such as ultra-stiffness and negative materials indices. In mechanical metamaterial design, three key modalities are typically involved, i.e., 3D…

We introduce submodel co-training, a regularization method related to co-training, self-distillation and stochastic depth. Given a neural network to be trained, for each sample we implicitly instantiate two altered networks, ``submodels'',…