Search for: All records

Human-annotated labels are often prone to noise, and the presence of such noise will degrade the performance of the resulting deep neural network (DNN) models. Much of the literature (with several recent exceptions) of learning with noisy labels focuses on the case when the label noise is independent of features. Practically, annotations errors tend to be instance-dependent and often depend on the difficulty levels of recognizing a certain task. Applying existing results from instance-independent settings would require a significant amount of estimation of noise rates. Therefore, providing theoretically rigorous solutions for learning with instance-dependent label noise remains a challenge. In this paper, we propose CORES (COnfidence REgularized Sample Sieve), which progressively sieves out corrupted examples. The implementation of CORES does not require specifying noise rates and yet we are able to provide theoretical guarantees of CORES in filtering out the corrupted examples. This high-quality sample sieve allows us to treat clean examples and the corrupted ones separately in training a DNN solution, and such a separation is shown to be advantageous in the instance-dependent noise setting. We demonstrate the performance of CORES^2 on CIFAR10 and CIFAR100 datasets with synthetic instance-dependent label noise and Clothing1M with real-world human noise. As of independent interests, our sample sieve provides a generic machinery for anatomizing noisy datasets and provides a flexible interface for various robust training techniques to further improve the performance. Code is available at https://github.com/UCSC-REAL/cores. 

It is important to collect credible training samples $(x,y)$ for building data-intensive learning systems (e.g., a deep learning system). Asking people to report complex distribution $p(x)$, though theoretically viable, is challenging in practice. This is primarily due to the cognitive loads required for human agents to form the report of this highly complicated information. While classical elicitation mechanisms apply to eliciting a complex and generative (and continuous) distribution $p(x)$, we are interested in eliciting samples $x_i \sim p(x)$ from agents directly. We coin the above problem sample elicitation. This paper introduces a deep learning aided method to incentivize credible sample contributions from self-interested and rational agents. We show that with an accurate estimation of a certain $f$-divergence function we can achieve approximate incentive compatibility in eliciting truthful samples. We then present an efficient estimator with theoretical guarantees via studying the variational forms of the $f$-divergence function. We also show a connection between this sample elicitation problem and $f$-GAN, and how this connection can help reconstruct an estimator of the distribution based on collected samples. Experiments on synthetic data, MNIST, and CIFAR-10 datasets demonstrate that our mechanism elicits truthful samples. Our implementation is available at https://github.com/weijiaheng/Credible-sample-elicitation.git. 

Knowing whether a published research result can be replicated is important. Carrying out direct replication of published research incurs a high cost. There are efforts tried to use machine learning aided methods to predict scientific claims’ replicability. However, existing machine learning aided approaches use only hand-extracted statistics features such as p-value, sample size, etc. without utilizing research papers’ text information and train only on a very small size of annotated data without making the most use of a large number of unlabeled articles. Therefore, it is desirable to develop effective machine learning aided automatic methods which can automatically extract text information as features so that we can benefit from Natural Language Processing techniques. Besides, we aim for an approach that benefits from both labeled and the large number of unlabeled data. In this paper, we propose two weakly supervised learning approaches that use automatically extracted text information of research papers to improve the prediction accuracy of research replication using both labeled and unlabeled datasets. Our experiments over real-world datasets show that our approaches obtain much better prediction performance compared to the supervised models utilizing only statistic features and a small size of labeled dataset. Further, we are able to achieve an accuracy of 75.76% for predicting the replicability of research. 

Although foreshock transients can generate strong magnetospheric Pc5 ultralow‐frequency (ULF) waves, whether they can modulate the energy of magnetospheric ions is still poorly understood. In this study, we analyze the strong magnetospheric ion energy modulations in a foreshock transient event on October 30, 2008, based on the magnetospheric observations by the time history of events and macroscale interactions during substorms A and D in the prenoon sector. ULF wave‐induceddrift accelerated the cold ions up to ∼10 keV and the enhanced ion fluxes have wave‐like patterns. There is another portion of enhanced ion fluxes from ∼0.8 to ∼10 keV but with strong energy dispersions in this event. By comparing the observations and the theoretical prediction, we for the first time found that the drift‐bounce resonances played a major role in modulating the energy of those ions with energy dispersions, during the interactions between the ions and the foreshock transient‐driven Pc5 ULF wave with growing and damping effects.

 

Nanocrystalline materials with superior properties are of great interest. Much is discussed about obtaining nanograins, but little is known about maintaining grain‐size uniformity that is critical for reliability. An especially intriguing question is whether it is possible to achieve a size distribution narrower than what Hillert theoretically predicted for normal grain growth, a possibility suggested—for growth with a higher growth exponent—by the generalized mean‐field theory of Lifshitz, Slyozov, Wagner (LSW), and Hillert but never realized in practice. Following a rationally designed two‐step sintering route, it has been made possible in bulk materials by taking advantage of the large growth exponent in the intermediate sintering stage to form a uniform microstructure despite residual porosity, and freezing the grain growth thereafter while continuing densification to reach full density. The bulk dense Al₂O₃ceramic thus obtained has an average grain size of 34 nm and a size distribution much narrower than Hillert's prediction. Bulk Al₂O₃with a grain‐size distribution narrower than the particle‐size distribution of starting powders is also demonstrated, as are highly uniform bulk engineering metals (refractory Mo and W‐Re alloy) and complex functional ceramics (BaTiO₃‐based alloys with superior dielectric strength and energy capacity).