The Data Deconflation Problem: Moving from Classical to Emerging Solutions

Data conflation refers to the superposition data produced by diverse processes resulting in complex, combined data objects. We define the data deconflation problem as the challenge of identifying and separating these complex data objects into their individual, constituent objects. Solutions to classical deconflation problems (e.g., the Cocktail Party Problem) use established linear algebra techniques, but it is not clear that those solutions are extendable to broader classes of conflated data objects. This paper surveys both classical and emerging data deconflation problems, as well as presenting an approach towards a general solution utilizing deep reinforcement learning and generative adversarial networks.

[1]  Simon S. Woo,et al.  Detecting Both Machine and Human Created Fake Face Images In the Wild , 2018, MPS@CCS.

[2]  Yoshua Bengio,et al.  Generative Adversarial Nets , 2014, NIPS.

[3]  Barak A. Pearlmutter,et al.  Survey of sparse and non‐sparse methods in source separation , 2005, Int. J. Imaging Syst. Technol..

[4]  Peter Henderson,et al.  An Introduction to Deep Reinforcement Learning , 2018, Found. Trends Mach. Learn..

[5]  K. Shapiro,et al.  Personal names and the attentional blink: a visual "cocktail party" effect. , 1997, Journal of experimental psychology. Human perception and performance.

[6]  Jong Chul Ye,et al.  CollaGAN: Collaborative GAN for Missing Image Data Imputation , 2019, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[7]  E. C. Cmm,et al.  on the Recognition of Speech, with , 2008 .

[8]  Zan Li,et al.  Time differences of arrival estimation of mixed interference signals using blind source separation based on wireless sensor networks , 2016, IET Signal Process..

[9]  Josh H. McDermott.  The cocktail party problem , 2009, Current Biology.

[10]  Maxine Eskénazi,et al.  Towards End-to-End Learning for Dialog State Tracking and Management using Deep Reinforcement Learning , 2016, SIGDIAL Conference.

[11]  Jonathon Shlens,et al.  Explaining and Harnessing Adversarial Examples , 2014, ICLR.

[12]  Vincent H. Berk,et al.  Process query systems for network security monitoring , 2005, SPIE Defense + Commercial Sensing.

[13]  Xiaojie Yuan,et al.  Missing value imputation in multivariate time series with end-to-end generative adversarial networks , 2021, Inf. Sci..

[14]  Vincent H. Berk,et al.  Covert Channel Detection Using Process Query Systems , 2005 .

[15]  Dong Yu,et al.  Past review, current progress, and challenges ahead on the cocktail party problem , 2018, Frontiers of Information Technology & Electronic Engineering.

[16]  Vincent H. Berk,et al.  Implementing Large-Scale Autonomic Server Monitoring Using Process Query Systems , 2005, Second International Conference on Autonomic Computing (ICAC'05).

[17]  Ying Zhang,et al.  Multivariate Time Series Imputation with Generative Adversarial Networks , 2018, NeurIPS.

[18]  Eleftherios Kofidis,et al.  Blind Source Separation: Fundamentals and Recent Advances (A Tutorial Overview Presented at SBrT-2001) , 2016, ArXiv.

[19]  Seymour Ginsburg,et al.  Synthesis of Minimal-State Machines , 1959, IRE Trans. Electron. Comput..

[20]  Vincent H. Berk,et al.  Process query systems , 2007, Computer.

[21]  Pierre Comon,et al.  Handbook of Blind Source Separation: Independent Component Analysis and Applications , 2010 .

[22]  Gabriel Dulac-Arnold,et al.  Challenges of Real-World Reinforcement Learning , 2019, ArXiv.

[23]  Jianfeng Gao,et al.  Deep Reinforcement Learning with a Natural Language Action Space , 2015, ACL.

[24]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[25]  Fred B. Schneider,et al.  Implementing fault-tolerant services using the state machine approach: a tutorial , 1990, CSUR.

[26]  Richard S. Sutton,et al.  Reinforcement Learning: An Introduction , 1998, IEEE Trans. Neural Networks.

[27]  Yan Wu,et al.  Optimizing agent behavior over long time scales by transporting value , 2018, Nature Communications.