Deep Entity Matching (EM) is one of the core research topics in data integration. Typical existing works construct EM models by training deep neural networks (DNNs) based on the training samples with onehot labels. However, these sharp supervision signals of onehot labels harm the generalization of EM models, causing them to overfit the training samples and perform badly in unseen datasets. To solve this problem, we first propose that the challenge of training a well-generalized EM model lies in achieving the compromise between fitting the training samples and imposing regularization, i.e., the bias-variance tradeoff. Then, we propose a novel Soft Target-EnhAnced Matching (Steam) framework, which exploits the automatically generated soft targets as label-wise regularizers to constrain the model training. Specifically, Steam regards the EM model trained in previous iteration as a virtual teacher and takes its softened output as the extra regularizer to train the EM model in the current iteration. As such, Steam effectively calibrates the obtained EM model, achieving the bias-variance tradeoff without any additional computational cost. We conduct extensive experiments over open datasets and the results show that our proposed Steam outperforms the state-of-the-art EM approaches in terms of effectiveness and label efficiency.

We uncover the structure, stability and electronic properties of polaronic defects in monolayer (ML) CeO2 by means of first-principles calculations, with special attention paid to the quantum confinement effect induced by dimensionality reduction. Results show that polaron can be more stabilized in ML CeO2 than in the bulk, while formation of oxygen vacancy (Vo2+) and polaron-vacancy complexes [(Vo2+-1polaron)1+, (Vo2+-2polaron)0] turns to be more difficult. The polaronic defect states sit deeper in energy within the band gap of ML CeO2 compared to the bulk case. We further demonstrate that the epitaxial strain in ceria film, as normally exists when grown on metal substrate, plays a crucial role in regulating the defect energetics and electronic structures. In particular, the formation energies of polarons, Vo2+, (Vo2+-1polaron)1+ and (Vo2+-2polaron)0 generally decrease with tensile strain, leading to controllable defect concentration with strain and temperature. This study not only provides physical insights into the polaronic defects in ultrathin oxide films, but also sheds light on their potential technological applications in nanoelectronics, fuel cells and catalysts.

No abstract

No abstract

No abstract