Classic machine learning methods are built on the i.i.d. assumption that training and testing data are independent and identically distributed. However, in real scenarios, the i.i.d. assumption can hardly be satisfied, rendering the sharp drop of classic machine learning algorithms' performances under distributional shifts, which indicates the significance of investigating the Out-of-Distribution generalization problem. Out-of-Distribution (OOD) generalization problem addresses the challenging setting where the testing distribution is unknown and different from the training. This paper serves as the first effort to systematically and comprehensively discuss the OOD generalization problem, from the definition, methodology, evaluation to the implications and future directions. Firstly, we provide the formal definition of the OOD generalization problem. Secondly, existing methods are categorized into three parts based on their positions in the whole learning pipeline, namely unsupervised representation learning, supervised model learning and optimization, and typical methods for each category are discussed in detail. We then demonstrate the theoretical connections of different categories, and introduce the commonly used datasets and evaluation metrics. Finally, we summarize the whole literature and raise some future directions for OOD generalization problem. The summary of OOD generalization methods reviewed in this survey can be found at http://out-of-distribution-generalization.com.

No abstract

No abstract

No abstract

As one of the main products produced by oral microorganisms, the role of lactic acid in the corrosion of titanium is very important. In this study, the corrosion behavior of titanium in artificial saliva with and without lactic acid were investigated by open-circuit potentials (OCPs), polarization curves and electrochemical impedance spectroscopy (EIS). OCP firstly increased with the amount of lactic acid from 0 to 3.2 g/L and then tended to decrease from 3.2 to 5.0 g/L. The corrosion of titanium was distinctly affected by lactic acid, and the corrosion rate increased with increasing the amount of lactic acid. At each concentration of lactic acid, the corrosion rate clearly increased with increasing the immersing time. Results of scanning electron microscopy (SEM) also indicated that lactic acid accelerated the pitting corrosion in artificial saliva. A probable mechanism was also proposed to explain the experimental results.

No abstract

No abstract

No abstract