In the field of machine learning, it is still a critical issue to identify and supervise the learned representation without manually intervening or intuition assistance to extract useful knowledge or serve for the downstream tasks. In this work, we focus on supervising the influential factors extracted by the variational autoencoder(VAE). The VAE is proposed to learn independent low dimension representation while facing the problem that sometimes pre-set factors are ignored. We argue that the mutual information of the input and each learned factor of the representation plays a necessary indicator of discovering the influential factors. We find the VAE objective inclines to induce mutual information sparsity in factor dimension over the data intrinsic dimension and therefore result in some non-influential factors whose function on data reconstruction could be ignored. We show mutual information also influences the lower bound of the VAE's reconstruction error and downstream classification task. To make such indicator applicable, we design an algorithm for calculating the mutual information for the VAE and prove its consistency. Experimental results on MNIST, CelebA and DEAP datasets show that mutual information can help determine influential factors, of which some are interpretable and can be used to further generation and classification tasks, and help discover the variant that connects with emotion on DEAP dataset.
Discovering and decoding latent mean-field structure with variational autoencoders
Department of Physics and the James Franck Institute, University of Chicago(芝加哥大学物理系及詹姆斯·弗兰克研究所);CuspAI;AMLab, University of Amsterdam(阿姆斯特丹大学AMLab);Leinweber Institute for Theoretical Physics(莱因韦伯理论物理研究所)
University of Oxford(牛津大学);University of Cambridge(剑桥大学);University College London(伦敦大学学院);Health Data Research UK(英国健康数据研究中心);The Alan Turing Institute(艾伦·图灵研究所);University of Manchester(曼彻斯特大学)
DIWIFT: Discovering Instance-wise Influential Features for Tabular Data
Guangdong Laboratory of Artificial Intelligence and Digital Economy (SZ)(广东省人工智能与数字经济实验室(深圳));Shenzhen University(深圳大学);Huawei Technologies Co Ltd(华为技术有限公司);Tencent(腾讯);Tsinghua-Berkeley Shenzhen Institute(清华-伯克利深圳学院)
Shandong Provincial Key Laboratory of Network Based Intelligent Computing(山东省网络智能计算重点实验室);University of Jinan(济南大学);Jinan, 250022, China(济南市,250022,中国)
The Use of Autoencoders for Discovering Patient Phenotypes
MIT CSAIL(麻省理工学院计算机科学与人工智能实验室)
我们使用自动编码器来创建潜在患者表型的低维嵌入,我们假设这些表型是决定不同患者对不同干预措施反应的决定因素。我们比较了自编码器的性能,以固定长度的级联时间步序列作为输入与经常性的序列到序列的自编码器。我们对来自Beth Israel Deaconess Hospital的最新MIMIC III数据集的约35,500名患者进行了评估。
Federated Topic Model and Model Pruning Based on Variational Autoencoder
Beijing Key Laboratory of Intelligent Communication Software and Multimedia(智能通信软件与多媒体北京重点实验室);Beijing University of Posts and Telecommunications(北京邮电大学);School of Economics and Management(经济管理学院)
Adversarially Learned Anomaly Detection on CMS Open Data: re-discovering the top quark
ETH Zurich(苏黎世联邦理工学院);California Institute of Technology(加州理工学院);CERN(欧洲核子研究组织)
我们应用逆向学习异常检测(ALAD)算法在大型强子对撞机的质子-质子碰撞中发现新的物理过程的问题。基于ALAD的异常检测与变分自编码器达到的性能相匹配,在某些情况下有很大的改进。在4.4 fb-1的8 TeV CMS开放数据上训练ALAD算法,我们展示了数据驱动的异常检测和表征如何在现实生活中工作,通过识别LHC的t-tbar实验签名的主要特征来重新发现顶夸克。
Center for Computing Research, Sandia National Laboratories(桑迪亚国家实验室计算研究中心);Applied Information Sciences Center, Sandia National Laboratories(桑迪亚国家实验室应用信息科学中心);School of Computing and Augmented Intelligence, Arizona State University(亚利桑那州立大学计算与增强智能学院);School of Engineering and Applied Science, University of Pennsylvania(宾夕法尼亚大学工程与应用科学学院)
Detecting Out-of-distribution Samples via Variational Auto-encoder with Reliable Uncertainty Estimation
Southern University of Science and Technology(南方科技大学);Chongqing Jiaotong University(重庆交通大学);Tsinghua University(清华大学);China Automotive Engineering Research Institute(中国汽车工程研究院股份有限公司);Dalian University of Technology(大连理工大学);Zhejiang University(浙江大学)
Institute of Information Engineering, Chinese Academy of Sciences(中国科学院信息工程研究所);School of Cyber Security, University of Chinese Academy of Sciences(中国科学院大学网络空间安全学院)
"Task-relevant autoencoding" enhances machine learning for human neuroscience
University of California, Irvine(加州大学欧文分校);Université de Montréal(蒙特利尔大学);Centre de recherche de l’institut universitaire en santé mentale de Montréal(蒙特利尔大学精神健康研究所研究中心);ATR Computational Neuroscience Laboratories(ATR计算神经科学实验室);University of Florida(佛罗里达大学);University of California Los Angeles(加州大学洛杉矶分校);RIKEN Center for Brain Science(理化学研究所脑科学中心)