As an effective data preprocessing step, feature selection has shown its effectiveness to prepare high-dimensional data for many machine learning tasks. The proliferation of high di-mension and huge volume big data, however, has brought major challenges, e.g. computation complexity and stability on noisy data, upon existing feature-selection techniques. This paper introduces a novel neural network-based feature selection architecture, dubbed Attention-based Feature Selec-tion (AFS). AFS consists of two detachable modules: an at-tention module for feature weight generation and a learning module for the problem modeling. The attention module for-mulates correlation problem among features and supervision target into a binary classification problem, supported by a shallow attention net for each feature. Feature weights are generated based on the distribution of respective feature se-lection patterns adjusted by backpropagation during the train-ing process. The detachable structure allows existing off-the-shelf models to be directly reused, which allows for much less training time, demands for the training data and requirements for expertise. A hybrid initialization method is also intro-duced to boost the selection accuracy for datasets without enough samples for feature weight generation. Experimental results show that AFS achieves the best accuracy and stability in comparison to several state-of-art feature selection algo-rithms upon both MNIST, noisy MNIST and several datasets with small samples.
Adaptive Feature Selection for End-to-End Speech Translation
School of Informatics, University of Edinburgh(爱丁堡大学信息学院);ILLC, University of Amsterdam(阿姆斯特丹大学语言、逻辑与计算研究所);Department of Computational Linguistics, University of Zurich(苏黎世大学计算语言学系)
语音信号中的信息不是均匀分布的,这使得端到端(E2 E)语音翻译(ST)学习关注信息特征成为额外的挑战。在本文中,我们提出了自适应特征选择(AFS)的编码器-解码器为基础的E2 E ST。我们首先预训练的ASR编码器和应用AFS动态估计每个编码的语音特征SR的重要性。ST编码器,堆叠在ASR编码器的顶部,然后从(冻结)ASR编码器接收过滤的功能。我们采用L0 DROP(Zhang等人,2020)作为AFS的骨干,并使其适应于相对于时间和特征维度来稀疏化语音特征。LibriSpeech En-Fr和MuST-C基准测试的结果表明,AFS通过修剪约84%的时间特征来促进ST的学习,产生约1.3-1.6 BLEU的平均翻译增益和约1.4倍的解码加速比。特别是,与级联基线相比,AFS减少了性能差距,并且在LibriSpeech En-Fr上的表现优于它,BLEU得分为18.56(没有数据增强)
Robust Bayesian optimization with reinforcement learned acquisition functions
Nanjing University of Aeronautics and Astronautics(南京航空航天大学);Collaborative Innovation Center of Novel Software Technology and Industrialization(新型软件技术与产业化协同创新中心);State Key Laboratory of Aerodynamics(空气动力学国家重点实验室)
Adaptive Feature Selection Guided Deep Forest for COVID-19 Classification with Chest CT
Nanjing University of Aeronautics and Astronautics(南京航空航天大学);The Third Hospital of Jilin University(吉林大学第三医院);Ruijin Hospital, Shanghai Jiao Tong University School of Medicine(上海交通大学医学院附属瑞金医院);Tongji Hospital, Tongji Medical College, Huazhong University of Science and Technology(华中科技大学同济医学院附属同济医院);Shanghai Public Health Clinical Center, Fudan University(复旦大学附属上海市公共卫生临床中心);Shanghai United Imaging Intelligence Co., Ltd.(上海联影智能科技有限公司);Qianjiang Central Hospital, Jishou University School of Medicine(吉首大学医学院附属黔江中心医院)
胸部计算机断层扫描(CT)成为辅助诊断新型冠状病毒病(COVID-19)的有效工具。由于COVID-19在全球范围内爆发,使用基于CT图像的COVID-19分类的计算机辅助诊断技术可以在很大程度上减轻临床医生的负担。在本文中,我们提出了一种自适应特征选择引导的深度森林(AFS-DF)的COVID-19分类的胸部CT图像的基础上。具体来说,我们首先从CT图像中提取特定位置的特征。然后,为了用相对小规模的数据捕获这些特征的高级表示,我们利用深森林模型来学习特征的高级表示。此外,我们提出了一种基于训练的深度森林模型的特征选择方法,以减少特征的冗余,其中特征选择可以自适应地与COVID-19分类模型相结合。我们在COVID-19数据集上评估了我们提出的AFS-DF,其中包括1495名COVID-19患者和1027名社区获得性肺炎(CAP)患者。该方法的准确性(ACC)、灵敏度(SEN)、特异性(SPE)和AUC分别为91.79%、93.05%、89.95%和96.35%。在COVID-19数据集上的实验结果表明,与4种广泛使用的机器学习方法相比,所提出的AFS-DF在COVID-19 vs. CAP分类中具有更好的性能。
Semi-Supervised Deep Sobolev Regression: Estimation and Variable Selection by ReQU Neural Network
Wuhan University(武汉大学);School of Mathematics and Statistics, Wuhan University(武汉大学数学与统计学院);National Center for Applied Mathematics in Hubei(湖北国家应用数学中心);Hubei Key Laboratory of Computational Science, Wuhan University(武汉大学湖北省计算科学重点实验室)
Semi-Supervised Multi-Label Feature Selection with Consistent Sparse Graph Learning
Peking University(北京大学);Hong Kong Polytechnic University(香港理工大学);Harbin Institute of Technology (Shenzhen)(哈尔滨工业大学(深圳));University of Science and Technology of China(中国科学技术大学);University of Texas at Arlington(德克萨斯大学阿灵顿分校);Communication University of China(中国传媒大学);Hangzhou Normal University(杭州师范大学)
Joint Laboratory of Data Science and Business Intelligence, School of Statistics, Southwestern University of Finance and Economics(数据科学与商业智能联合实验室,统计学院,西南财经大学);Department of Electrical Engineering and Computer Science, University of Kansas(电气工程与计算机科学系,堪萨斯大学);JD Intelligent Cities Research and JD Intelligent Cities Business Unit(京东智能城市研究部和京东智能城市业务部);School of Computing and Artificial Intelligence, Southwest Jiaotong University(计算与人工智能学院,西南交通大学)
Latent regularization for feature selection using kernel methods in tumor classification
Institut Charles Delaunay, Universite de Technologie de Troyes(特鲁瓦理工大学夏尔·德洛纳研究所);Biomedicine Research Institute of Buenos Aires - Max Planck Partner Institute(布宜诺斯艾利斯生物医学研究所-马克斯·普朗克伙伴研究所);Universidad Tecnologica Nacional Buenos Aires(布宜诺斯艾利斯国立理工大学)
Semi-Supervised Data Programming with Subset Selection
IIT Bombay(印度理工学院孟买分校);The University of Texas at Dallas(德克萨斯大学达拉斯分校)
数据编程的范式,它使用弱监督的形式的规则/标签功能,和半监督学习,它增加了大量的未标记的数据集少量的标记数据,在几个文本分类的情况下,显示出很大的希望。在这项工作中,我们认为,通过不使用任何标记的数据,基于数据编程的方法可以产生次优性能,特别是当标签函数是嘈杂的。这项工作的第一个贡献是引入一个框架,\model,这是一个半监督的数据编程范式,学习\emph{joint model},有效地使用规则/标签功能以及半监督损失函数的特征空间。接下来,我们还研究了\modelss,它在联合半监督数据编程目标和\emph{selects}的基础上进行子集选择,这是一组可以用作\model标记集的示例。\modelss的目标是确保标记的数据可以通过\emph{complement}标记功能,从而受益于数据编程以及适当选择的人类标记数据。我们证明,通过有效地结合半监督,数据编程和子集选择范式,我们显着优于目前的最先进的七个公开可用的数据集。\footnote{The source code is available at \url{https://github.com/ayushbits/Semi-Supervised-LFs-Subset-Selection}}
Evaluating Supervised Machine Learning Models: Principles, Pitfalls, and Metric Selection
Jiangsu Key Laboratory of Big Data Security and Intelligent Processing, Nanjing University of Posts and Telecommunications(江苏大数据安全与智能处理重点实验室,南京邮电大学);University of Brighton(布莱顿大学);University of Lancashire(兰开夏大学);School of Cyber Science and Engineering, Southeast University(东南大学信息科学与工程学院)