非平行的多域语音转换方法（例如Stargan-VC）在许多情况下已被广泛应用。但是，这些模型的培训通常由于其复杂的对抗网络体系结构而构成挑战。为了解决这个问题，在这项工作中，我们利用最先进的对比学习技术，并将有效的暹罗网络结构纳入Stargan歧视者。我们的方法称为Simsiam-Stargan-VC，它提高了训练稳定性，并有效地防止了训练过程中的歧视者过度拟合问题。我们对语音转换挑战（VCC 2018）数据集进行了实验，并进行了用户研究，以验证我们的框架性能。我们的实验结果表明，Simsiam-Stargan-VC在客观和主观指标方面显着优于现有的Stargan-VC方法。

深度神经网络可以捕获查询和文档之间的复杂交互历史信息，因为它们的许多复杂的非线性单元，使它们能够提供正确的搜索建议。但是，在现实情况下，服务提供商经常面临更复杂的障碍，例如部署成本限制和公平要求。已经提出了将训练有素的复杂模型（教师）转移到简单模型（学生）的知识的知识蒸馏，以减轻前者的关注，但最佳当前蒸馏方法仅着重于如何使学生模型模仿教师模型的预测。为了更好地促进深层模型的应用，我们建议基于知识蒸馏的公平信息检索框架。该框架可以改善模型的基于暴露的公平性，同时大大降低模型大小。我们在三个巨大数据集上进行的广泛实验表明，我们提出的框架可以将模型尺寸降低到其原始尺寸的最小1％，同时保持其黑盒状态。它还将公平性能提高15％〜46％，同时保持高水平的建议效率。

尽管深度神经网络（DNNS）在音频分类任务中取得了巨大的成功，但它们的不确定性校准仍未得到探索。当它确定其预测时，应进行良好的模型应准确，并表明何时可能不准确。在这项工作中，我们研究了深度音频分类器的不确定性校准。特别是，我们从经验上研究了流行校准方法的性能：（i）蒙特卡洛辍学方法，（ii）集合，（iii）局灶性损失和（iv）光谱范围差异高斯工艺（SNGP），在音频分类数据集上。为此，我们评估了（I-IV），以应对环境声音和音乐流派分类的任务。结果表明，未校准的深度音频分类器可能过于自信，并且SNGP在本文的两个数据集中表现最好，并且非常有效。

联合学习（FL）和分裂学习（SL）是两种新兴的协作学习方法，可能会极大地促进物联网（IoT）中无处不在的智能。联合学习使机器学习（ML）模型在本地培训的模型使用私人数据汇总为全球模型。分裂学习使ML模型的不同部分可以在学习框架中对不同工人进行协作培训。联合学习和分裂学习，每个学习都有独特的优势和各自的局限性，可能会相互补充，在物联网中无处不在的智能。因此，联合学习和分裂学习的结合最近成为一个活跃的研究领域，引起了广泛的兴趣。在本文中，我们回顾了联合学习和拆分学习方面的最新发展，并介绍了有关最先进技术的调查，该技术用于将这两种学习方法组合在基于边缘计算的物联网环境中。我们还确定了一些开放问题，并讨论了该领域未来研究的可能方向，希望进一步引起研究界对这个新兴领域的兴趣。

通过使用低成本，远程，无维护的无线传感器进行增强，数十亿个日常对象可能会成为物联网（IoT）的一部分。射频识别（RFID）是一种低成本的无线技术，可以实现这一愿景，但是它受到短暂的通信范围和缺乏足够的能量来限制辅助电子和传感器。在这里，我们探讨了柔性钙钛矿光伏电池的使用，以提供半邮用RFID标签的外部功率，以增加外部电子设备（例如微控制器和数字传感器）的范围和能量可用性。钙钛矿是有趣的材料，具有开发高性能，低成本，可调节性（吸收不同的光谱）和柔性轻能量收割机的可能性。在标准测试条件下，我们的塑料底物上的原型钙钛矿光伏细胞的效率为13％，电压为0.88 V。我们构建了由这些柔性光伏电池供电的RFID传感器的原型原型，以展示现实世界的应用。我们对原型的评估表明：i）柔性PV细胞耐用至5 mm的弯曲半径，相对效率仅下降20％； ii）RFID通信范围增加了5倍，并满足能源需求（10-350 microwatt）以实现自动无线传感器； iii）钙钛矿动力无线传感器启用许多无电池传感应用程序（例如，易腐烂的良好监控，仓库自动化）

实现一般逆设计可以通过用户定义的属性极大地加速对新材料的发现。然而，最先进的生成模型往往限于特定的组成或晶体结构。这里，我们提出了一种能够一般逆设计的框架（不限于给定的一组元件或晶体结构），其具有在实际和往复空间中编码晶体的广义可逆表示，以及来自变分的属性结构潜空间autoencoder（vae）。在三种设计情况下，该框架通过用户定义的形成能量，带隙，热电（TE）功率因数和组合产生142个新晶体。在训练数据库中缺席的这些生成的晶体通过第一原理计算验证。成功率（验证的第一原理验证的目标圆形晶体/数量的设计晶体）范围为7.1％和38.9％。这些结果表示利用生成模型朝着性质驱动的一般逆设计的重要步骤，尽管在与实验合成结合时仍然存在实际挑战。

Video action segmentation aims to slice the video into several action segments. Recently, timestamp supervision has received much attention due to lower annotation costs. We find the frames near the boundaries of action segments are in the transition region between two consecutive actions and have unclear semantics, which we call ambiguous intervals. Most existing methods iteratively generate pseudo-labels for all frames in each video to train the segmentation model. However, ambiguous intervals are more likely to be assigned with noisy and incorrect pseudo-labels, which leads to performance degradation. We propose a novel framework to train the model under timestamp supervision including the following two parts. First, pseudo-label ensembling generates pseudo-label sequences with ambiguous intervals, where the frames have no pseudo-labels. Second, iterative clustering iteratively propagates the pseudo-labels to the ambiguous intervals by clustering, and thus updates the pseudo-label sequences to train the model. We further introduce a clustering loss, which encourages the features of frames within the same action segment more compact. Extensive experiments show the effectiveness of our method.

Deep neural networks (DNNs) are sensitive and susceptible to tiny perturbation by adversarial attacks which causes erroneous predictions. Various methods, including adversarial defense and uncertainty inference (UI), have been developed in recent years to overcome the adversarial attacks. In this paper, we propose a multi-head uncertainty inference (MH-UI) framework for detecting adversarial attack examples. We adopt a multi-head architecture with multiple prediction heads (i.e., classifiers) to obtain predictions from different depths in the DNNs and introduce shallow information for the UI. Using independent heads at different depths, the normalized predictions are assumed to follow the same Dirichlet distribution, and we estimate distribution parameter of it by moment matching. Cognitive uncertainty brought by the adversarial attacks will be reflected and amplified on the distribution. Experimental results show that the proposed MH-UI framework can outperform all the referred UI methods in the adversarial attack detection task with different settings.

We present Pre-trained Machine Reader (PMR), a novel method to retrofit Pre-trained Language Models (PLMs) into Machine Reading Comprehension (MRC) models without acquiring labeled data. PMR is capable of resolving the discrepancy between model pre-training and downstream fine-tuning of existing PLMs, and provides a unified solver for tackling various extraction tasks. To achieve this, we construct a large volume of general-purpose and high-quality MRC-style training data with the help of Wikipedia hyperlinks and design a Wiki Anchor Extraction task to guide the MRC-style pre-training process. Although conceptually simple, PMR is particularly effective in solving extraction tasks including Extractive Question Answering and Named Entity Recognition, where it shows tremendous improvements over previous approaches especially under low-resource settings. Moreover, viewing sequence classification task as a special case of extraction task in our MRC formulation, PMR is even capable to extract high-quality rationales to explain the classification process, providing more explainability of the predictions.

The opaqueness of the multi-hop fact verification model imposes imperative requirements for explainability. One feasible way is to extract rationales, a subset of inputs, where the performance of prediction drops dramatically when being removed. Though being explainable, most rationale extraction methods for multi-hop fact verification explore the semantic information within each piece of evidence individually, while ignoring the topological information interaction among different pieces of evidence. Intuitively, a faithful rationale bears complementary information being able to extract other rationales through the multi-hop reasoning process. To tackle such disadvantages, we cast explainable multi-hop fact verification as subgraph extraction, which can be solved based on graph convolutional network (GCN) with salience-aware graph learning. In specific, GCN is utilized to incorporate the topological interaction information among multiple pieces of evidence for learning evidence representation. Meanwhile, to alleviate the influence of noisy evidence, the salience-aware graph perturbation is induced into the message passing of GCN. Moreover, the multi-task model with three diagnostic properties of rationale is elaborately designed to improve the quality of an explanation without any explicit annotations. Experimental results on the FEVEROUS benchmark show significant gains over previous state-of-the-art methods for both rationale extraction and fact verification.