Search for: All records

To address the sample selection bias between the training and test data, previous research works focus on reweighing biased training data to match the test data and then building classification models on there weighed raining data. However, how to achieve fairness in the built classification models is under-explored. In this paper, we propose a framework for robust and fair learning under sample selection bias. Our framework adopts there weighing estimation approach for bias correction and the minimax robust estimation approach for achieving robustness on prediction accuracy. Moreover, during the minimax optimization, the fairness is achieved under the worst case, which guarantees the model’s fairness on test data. We further develop two algorithms to handle sample selection bias when test data is both available and unavailable.

In differentially private stochastic gradient descent (DPSGD), gradient clipping and random noise addition disproportionately affect underrepresented and complex classes and subgroups. As a consequence, DPSGD has disparate impact: the accuracy of a model trained using DPSGD tends to decrease more on these classes and subgroups vs. the original, non-private model. If the original model is unfair in the sense that its accuracy is not the same across all subgroups, DPSGD exacerbates this unfairness. In this work, we study the inequality in utility loss due to differential privacy, which compares the changes in prediction accuracy w.r.t. each group between the private model and the non-private model. We analyze the cost of privacy w.r.t. each group and explain how the group sample size along with other factors is related to the privacy impact on group accuracy. Furthermore, we propose a modified DPSGD algorithm, called DPSGD-F, to achieve differential privacy, equal costs of differential privacy, and good utility. DPSGD-F adaptively adjusts the contribution of samples in a group depending on the group clipping bias such that differential privacy has no disparate impact on group accuracy. Our experimental evaluation shows the effectiveness of our removal algorithm on achieving equal costs of differential privacy withmore »satisfactory utility.« less

Abstract Ammonium vanadate with bronze structure (NH 4 V 4 O 10 ) is a promising cathode material for zinc-ion batteries due to its high specific capacity and low cost. However, the extraction of $${\text{NH}}_{{4}}^{ + }$$ NH 4 + at a high voltage during charge/discharge processes leads to irreversible reaction and structure degradation. In this work, partial $${\text{NH}}_{{4}}^{ + }$$ NH 4 + ions were pre-removed from NH 4 V 4 O 10 through heat treatment; NH 4 V 4 O 10 nanosheets were directly grown on carbon cloth through hydrothermal method. Deficient NH 4 V 4 O 10 (denoted as NVO), with enlarged interlayer spacing, facilitated fast zinc ions transport and high storage capacity and ensured the highly reversible electrochemical reaction and the good stability of layered structure. The NVO nanosheets delivered a high specific capacity of 457 mAh g −1 at a current density of 100 mA g −1 and a capacity retention of 81% over 1000 cycles at 2 A g −1 . The initial Coulombic efficiency of NVO could reach up to 97% compared to 85% of NH 4 V 4 O 10 and maintain almost 100% during cycling, indicating the high reaction reversibility in NVO electrode.

Low surface brightness (LSB) galaxies are galaxies with central surface brightness fainter than the night sky. Due to the faint nature of LSB galaxies and the comparable sky background, it is difficult to search LSB galaxies automatically and efficiently from large sky survey. In this study, we established the low surface brightness galaxies autodetect (LSBG-AD) model, which is a data-driven model for end-to-end detection of LSB galaxies from Sloan Digital Sky Survey (SDSS) images. Object-detection techniques based on deep learning are applied to the SDSS field images to identify LSB galaxies and estimate their coordinates at the same time. Applying LSBG-AD to 1120 SDSS images, we detected 1197 LSB galaxy candidates, of which 1081 samples are already known and 116 samples are newly found candidates. The B-band central surface brightness of the candidates searched by the model ranges from 22 to 24 mag arcsec−2, quite consistent with the surface brightness distribution of the standard sample. A total of 96.46 per cent of LSB galaxy candidates have an axial ratio (b/a) greater than 0.3, and 92.04 per cent of them have $fracDev\_r$ < 0.4, which is also consistent with the standard sample. The results show that the LSBG-AD model learns the features of LSB galaxiesmore »of the training samples well, and can be used to search LSB galaxies without using photometric parameters. Next, this method will be used to develop efficient algorithms to detect LSB galaxies from massive images of the next-generation observatories.

« less