October 20, 2019

2745 words 13 mins read

Paper Group ANR 103

Exploring Connections Between Active Learning and Model Extraction. Focusing on the Big Picture: Insights into a Systems Approach to Deep Learning for Satellite Imagery. Empirical observations of ultraslow diffusion driven by the fractional dynamics in languages: Dynamical statistical properties of word counts of already popular words. Are screenin …

Exploring Connections Between Active Learning and Model Extraction


Title	Exploring Connections Between Active Learning and Model Extraction
Authors	Varun Chandrasekaran, Kamalika Chaudhuri, Irene Giacomelli, Somesh Jha, Songbai Yan
Abstract	Machine learning is being increasingly used by individuals, research institutions, and corporations. This has resulted in the surge of Machine Learning-as-a-Service (MLaaS) - cloud services that provide (a) tools and resources to learn the model, and (b) a user-friendly query interface to access the model. However, such MLaaS systems raise privacy concerns such as model extraction. In model extraction attacks, adversaries maliciously exploit the query interface to steal the model. More precisely, in a model extraction attack, a good approximation of a sensitive or proprietary model held by the server is extracted (i.e. learned) by a dishonest user who interacts with the server only via the query interface. This attack was introduced by Tramer et al. at the 2016 USENIX Security Symposium, where practical attacks for various models were shown. We believe that better understanding the efficacy of model extraction attacks is paramount to designing secure MLaaS systems. To that end, we take the first step by (a) formalizing model extraction and discussing possible defense strategies, and (b) drawing parallels between model extraction and established area of active learning. In particular, we show that recent advancements in the active learning domain can be used to implement powerful model extraction attacks, and investigate possible defense strategies.
Tasks	Active Learning
Published	2018-11-05
URL	https://arxiv.org/abs/1811.02054v6
PDF	https://arxiv.org/pdf/1811.02054v6.pdf
PWC	https://paperswithcode.com/paper/exploring-connections-between-active-learning
Repo
Framework

Focusing on the Big Picture: Insights into a Systems Approach to Deep Learning for Satellite Imagery


Title	Focusing on the Big Picture: Insights into a Systems Approach to Deep Learning for Satellite Imagery
Authors	Ritwik Gupta, Carson D. Sestili, Javier A. Vazquez-Trejo, Matthew E. Gaston
Abstract	Deep learning tasks are often complicated and require a variety of components working together efficiently to perform well. Due to the often large scale of these tasks, there is a necessity to iterate quickly in order to attempt a variety of methods and to find and fix bugs. While participating in IARPA’s Functional Map of the World challenge, we identified challenges along the entire deep learning pipeline and found various solutions to these challenges. In this paper, we present the performance, engineering, and deep learning considerations with processing and modeling data, as well as underlying infrastructure considerations that support large-scale deep learning tasks. We also discuss insights and observations with regard to satellite imagery and deep learning for image classification.
Tasks	Image Classification
Published	2018-11-12
URL	http://arxiv.org/abs/1811.04893v1
PDF	http://arxiv.org/pdf/1811.04893v1.pdf
PWC	https://paperswithcode.com/paper/focusing-on-the-big-picture-insights-into-a
Repo
Framework

Empirical observations of ultraslow diffusion driven by the fractional dynamics in languages: Dynamical statistical properties of word counts of already popular words


Title	Empirical observations of ultraslow diffusion driven by the fractional dynamics in languages: Dynamical statistical properties of word counts of already popular words
Authors	Hayafumi Watanabe
Abstract	Ultraslow diffusion (i.e. logarithmic diffusion) has been extensively studied theoretically, but has hardly been observed empirically. In this paper, firstly, we find the ultraslow-like diffusion of the time-series of word counts of already popular words by analysing three different nationwide language databases: (i) newspaper articles (Japanese), (ii) blog articles (Japanese), and (iii) page views of Wikipedia (English, French, Chinese, and Japanese). Secondly, we use theoretical analysis to show that this diffusion is basically explained by the random walk model with the power-law forgetting with the exponent $\beta \approx 0.5$, which is related to the fractional Langevin equation. The exponent $\beta$ characterises the speed of forgetting and $\beta \approx 0.5$ corresponds to (i) the border (or thresholds) between the stationary and the nonstationary and (ii) the right-in-the-middle dynamics between the IID noise for $\beta=1$ and the normal random walk for $\beta=0$. Thirdly, the generative model of the time-series of word counts of already popular words, which is a kind of Poisson process with the Poisson parameter sampled by the above-mentioned random walk model, can almost reproduce not only the empirical mean-squared displacement but also the power spectrum density and the probability density function.
Tasks	Time Series
Published	2018-01-24
URL	http://arxiv.org/abs/1801.07948v5
PDF	http://arxiv.org/pdf/1801.07948v5.pdf
PWC	https://paperswithcode.com/paper/empirical-observations-of-ultraslow-diffusion
Repo
Framework

Are screening methods useful in feature selection? An empirical study


Title	Are screening methods useful in feature selection? An empirical study
Authors	Mingyuan Wang, Adrian Barbu
Abstract	Filter or screening methods are often used as a preprocessing step for reducing the number of variables used by a learning algorithm in obtaining a classification or regression model. While there are many such filter methods, there is a need for an objective evaluation of these methods. Such an evaluation is needed to compare them with each other and also to answer whether they are at all useful, or a learning algorithm could do a better job without them. For this purpose, many popular screening methods are partnered in this paper with three regression learners and five classification learners and evaluated on ten real datasets to obtain accuracy criteria such as R-square and area under the ROC curve (AUC). The obtained results are compared through curve plots and comparison tables in order to find out whether screening methods help improve the performance of learning algorithms and how they fare with each other. Our findings revealed that the screening methods were useful in improving the prediction of the best learner on two regression and two classification datasets out of the ten datasets evaluated.
Tasks	Feature Selection
Published	2018-09-14
URL	https://arxiv.org/abs/1809.05465v3
PDF	https://arxiv.org/pdf/1809.05465v3.pdf
PWC	https://paperswithcode.com/paper/are-screening-methods-useful-in-feature
Repo
Framework

Average performance analysis of the stochastic gradient method for online PCA


Title	Average performance analysis of the stochastic gradient method for online PCA
Authors	Stephane Chretien, Christophe Guyeux, Zhen-Wai Olivier HO
Abstract	This paper studies the complexity of the stochastic gradient algorithm for PCA when the data are observed in a streaming setting. We also propose an online approach for selecting the learning rate. Simulation experiments confirm the practical relevance of the plain stochastic gradient approach and that drastic improvements can be achieved by learning the learning rate.
Tasks
Published	2018-04-03
URL	http://arxiv.org/abs/1804.01071v1
PDF	http://arxiv.org/pdf/1804.01071v1.pdf
PWC	https://paperswithcode.com/paper/average-performance-analysis-of-the
Repo
Framework

Extending Modular Semantics for Bipolar Weighted Argumentation (Technical Report)


Title	Extending Modular Semantics for Bipolar Weighted Argumentation (Technical Report)
Authors	Nico Potyka
Abstract	Weighted bipolar argumentation frameworks offer a tool for decision support and social media analysis. Arguments are evaluated by an iterative procedure that takes initial weights and attack and support relations into account. Until recently, convergence of these iterative procedures was not very well understood in cyclic graphs. Mossakowski and Neuhaus recently introduced a unification of different approaches and proved first convergence and divergence results. We build up on this work, simplify and generalize convergence results and complement them with runtime guarantees. As it turns out, there is a tradeoff between semantics’ convergence guarantees and their ability to move strength values away from the initial weights. We demonstrate that divergence problems can be avoided without this tradeoff by continuizing semantics. Semantically, we extend the framework with a Duality property that assures a symmetric impact of attack and support relations. We also present a Java implementation of modular semantics and explain the practical usefulness of the theoretical ideas.
Tasks
Published	2018-09-19
URL	http://arxiv.org/abs/1809.07133v2
PDF	http://arxiv.org/pdf/1809.07133v2.pdf
PWC	https://paperswithcode.com/paper/extending-modular-semantics-for-bipolar
Repo
Framework

End-to-End Parkinson Disease Diagnosis using Brain MR-Images by 3D-CNN


Title	End-to-End Parkinson Disease Diagnosis using Brain MR-Images by 3D-CNN
Authors	Soheil Esmaeilzadeh, Yao Yang, Ehsan Adeli
Abstract	In this work, we use a deep learning framework for simultaneous classification and regression of Parkinson disease diagnosis based on MR-Images and personal information (i.e. age, gender). We intend to facilitate and increase the confidence in Parkinson disease diagnosis through our deep learning framework.
Tasks
Published	2018-06-13
URL	http://arxiv.org/abs/1806.05233v1
PDF	http://arxiv.org/pdf/1806.05233v1.pdf
PWC	https://paperswithcode.com/paper/end-to-end-parkinson-disease-diagnosis-using
Repo
Framework

Adaptive System Identification Using LMS Algorithm Integrated with Evolutionary Computation


Title	Adaptive System Identification Using LMS Algorithm Integrated with Evolutionary Computation
Authors	Ibraheem Kasim Ibraheem
Abstract	System identification is an exceptionally expansive topic and of remarkable significance in the discipline of signal processing and communication. Our goal in this paper is to show how simple adaptive FIR and IIR filters can be used in system modeling and demonstrating the application of adaptive system identification. The main objective of our research is to study the LMS algorithm and its improvement by the genetic search approach, namely, LMS-GA, to search the multi-modal error surface of the IIR filter to avoid local minima and finding the optimal weight vector when only measured or estimated data are available. Convergence analysis of the LMS algorithm in the case of coloured input signal, i.e., correlated input signal is demonstrated on adaptive FIR filter via power spectral density of the input signals and Fourier transform of the autocorrelation matrix of the input signal. Simulations have been carried out on adaptive filtering of FIR and IIR filters and tested on white and coloured input signals to validate the powerfulness of the genetic-based LMS algorithm.
Tasks
Published	2018-05-30
URL	http://arxiv.org/abs/1806.01782v2
PDF	http://arxiv.org/pdf/1806.01782v2.pdf
PWC	https://paperswithcode.com/paper/adaptive-system-identification-using-lms
Repo
Framework

A generalized parametric 3D shape representation for articulated pose estimation


Title	A generalized parametric 3D shape representation for articulated pose estimation
Authors	Meng Ding, Guoliang Fan
Abstract	We present a novel parametric 3D shape representation, Generalized sum of Gaussians (G-SoG), which is particularly suitable for pose estimation of articulated objects. Compared with the original sum-of-Gaussians (SoG), G-SoG can handle both isotropic and anisotropic Gaussians, leading to a more flexible and adaptable shape representation yet with much fewer anisotropic Gaussians involved. An articulated shape template can be developed by embedding G-SoG in a tree-structured skeleton model to represent an articulated object. We further derive a differentiable similarity function between G-SoG (the template) and SoG (observed data) that can be optimized analytically for efficient pose estimation. The experimental results on a standard human pose estimation dataset show the effectiveness and advantages of G-SoG over the original SoG as well as the promise compared with the recent algorithms that use more complicated shape models.
Tasks	3D Shape Representation, Pose Estimation
Published	2018-03-05
URL	http://arxiv.org/abs/1803.01780v1
PDF	http://arxiv.org/pdf/1803.01780v1.pdf
PWC	https://paperswithcode.com/paper/a-generalized-parametric-3d-shape
Repo
Framework

Detecting Linguistic Characteristics of Alzheimer’s Dementia by Interpreting Neural Models


Title	Detecting Linguistic Characteristics of Alzheimer’s Dementia by Interpreting Neural Models
Authors	Sweta Karlekar, Tong Niu, Mohit Bansal
Abstract	Alzheimer’s disease (AD) is an irreversible and progressive brain disease that can be stopped or slowed down with medical treatment. Language changes serve as a sign that a patient’s cognitive functions have been impacted, potentially leading to early diagnosis. In this work, we use NLP techniques to classify and analyze the linguistic characteristics of AD patients using the DementiaBank dataset. We apply three neural models based on CNNs, LSTM-RNNs, and their combination, to distinguish between language samples from AD and control patients. We achieve a new independent benchmark accuracy for the AD classification task. More importantly, we next interpret what these neural models have learned about the linguistic characteristics of AD patients, via analysis based on activation clustering and first-derivative saliency techniques. We then perform novel automatic pattern discovery inside activation clusters, and consolidate AD patients’ distinctive grammar patterns. Additionally, we show that first derivative saliency can not only rediscover previous language patterns of AD patients, but also shed light on the limitations of neural models. Lastly, we also include analysis of gender-separated AD data.
Tasks
Published	2018-04-17
URL	http://arxiv.org/abs/1804.06440v1
PDF	http://arxiv.org/pdf/1804.06440v1.pdf
PWC	https://paperswithcode.com/paper/detecting-linguistic-characteristics-of-1
Repo
Framework

Using Multitask Learning to Improve 12-Lead Electrocardiogram Classification


Title	Using Multitask Learning to Improve 12-Lead Electrocardiogram Classification
Authors	J. Weston Hughes, Taylor Sittler, Anthony D. Joseph, Jeffrey E. Olgin, Joseph E. Gonzalez, Geoffrey H. Tison
Abstract	We develop a multi-task convolutional neural network (CNN) to classify multiple diagnoses from 12-lead electrocardiograms (ECGs) using a dataset comprised of over 40,000 ECGs, with labels derived from cardiologist clinical interpretations. Since many clinically important classes can occur in low frequencies, approaches are needed to improve performance on rare classes. We compare the performance of several single-class classifiers on rare classes to a multi-headed classifier across all available classes. We demonstrate that the addition of common classes can significantly improve CNN performance on rarer classes when compared to a model trained on the rarer class in isolation. Using this method, we develop a model with high performance as measured by F1 score on multiple clinically relevant classes compared against the gold-standard cardiologist interpretation.
Tasks
Published	2018-12-03
URL	http://arxiv.org/abs/1812.00497v2
PDF	http://arxiv.org/pdf/1812.00497v2.pdf
PWC	https://paperswithcode.com/paper/using-multitask-learning-to-improve-12-lead
Repo
Framework

Convolutional Sequence to Sequence Non-intrusive Load Monitoring


Title	Convolutional Sequence to Sequence Non-intrusive Load Monitoring
Authors	Kunjin Chen, Qin Wang, Ziyu He, Kunlong Chen, Jun Hu, Jinliang He
Abstract	A convolutional sequence to sequence non-intrusive load monitoring model is proposed in this paper. Gated linear unit convolutional layers are used to extract information from the sequences of aggregate electricity consumption. Residual blocks are also introduced to refine the output of the neural network. The partially overlapped output sequences of the network are averaged to produce the final output of the model. We apply the proposed model to the REDD dataset and compare it with the convolutional sequence to point model in the literature. Results show that the proposed model is able to give satisfactory disaggregation performance for appliances with varied characteristics.
Tasks	Non-Intrusive Load Monitoring
Published	2018-06-06
URL	http://arxiv.org/abs/1806.02078v1
PDF	http://arxiv.org/pdf/1806.02078v1.pdf
PWC	https://paperswithcode.com/paper/convolutional-sequence-to-sequence-non
Repo
Framework

You Shall Know the Most Frequent Sense by the Company it Keeps


Title	You Shall Know the Most Frequent Sense by the Company it Keeps
Authors	Bradley Hauer, Yixing Luan, Grzegorz Kondrak
Abstract	Identification of the most frequent sense of a polysemous word is an important semantic task. We introduce two concepts that can benefit MFS detection: companions, which are the most frequently co-occurring words, and the most frequent translation in a bitext. We present two novel methods that incorporate these new concepts, and show that they advance the state of the art on MFS detection.
Tasks
Published	2018-08-21
URL	http://arxiv.org/abs/1808.06729v3
PDF	http://arxiv.org/pdf/1808.06729v3.pdf
PWC	https://paperswithcode.com/paper/you-shall-know-the-most-frequent-sense-by-the
Repo
Framework

Pose Guided Human Video Generation


Title	Pose Guided Human Video Generation
Authors	Ceyuan Yang, Zhe Wang, Xinge Zhu, Chen Huang, Jianping Shi, Dahua Lin
Abstract	Due to the emergence of Generative Adversarial Networks, video synthesis has witnessed exceptional breakthroughs. However, existing methods lack a proper representation to explicitly control the dynamics in videos. Human pose, on the other hand, can represent motion patterns intrinsically and interpretably, and impose the geometric constraints regardless of appearance. In this paper, we propose a pose guided method to synthesize human videos in a disentangled way: plausible motion prediction and coherent appearance generation. In the first stage, a Pose Sequence Generative Adversarial Network (PSGAN) learns in an adversarial manner to yield pose sequences conditioned on the class label. In the second stage, a Semantic Consistent Generative Adversarial Network (SCGAN) generates video frames from the poses while preserving coherent appearances in the input image. By enforcing semantic consistency between the generated and ground-truth poses at a high feature level, our SCGAN is robust to noisy or abnormal poses. Extensive experiments on both human action and human face datasets manifest the superiority of the proposed method over other state-of-the-arts.
Tasks	motion prediction, Video Generation
Published	2018-07-30
URL	http://arxiv.org/abs/1807.11152v1
PDF	http://arxiv.org/pdf/1807.11152v1.pdf
PWC	https://paperswithcode.com/paper/pose-guided-human-video-generation
Repo
Framework

Region Convolutional Features for Multi-Label Remote Sensing Image Retrieval


Title	Region Convolutional Features for Multi-Label Remote Sensing Image Retrieval
Authors	Weixun Zhou, Xueqing Deng, Zhenfeng Shao
Abstract	Conventional remote sensing image retrieval (RSIR) systems usually perform single-label retrieval where each image is annotated by a single label representing the most significant semantic content of the image. This assumption, however, ignores the complexity of remote sensing images, where an image might have multiple classes (i.e., multiple labels), thus resulting in worse retrieval performance. We therefore propose a novel multi-label RSIR approach with fully convolutional networks (FCN). In our approach, we first train a FCN model using a pixel-wise labeled dataset,and the trained FCN is then used to predict the segmentation maps of each image in the considered archive. We finally extract region convolutional features of each image based on its segmentation map.The region features can be either used to perform region-based retrieval or further post-processed to obtain a feature vector for similarity measure. The experimental results show that our approach achieves state-of-the-art performance in contrast to conventional single-label and recent multi-label RSIR approaches.
Tasks	Image Retrieval
Published	2018-07-23
URL	http://arxiv.org/abs/1807.08634v1
PDF	http://arxiv.org/pdf/1807.08634v1.pdf
PWC	https://paperswithcode.com/paper/region-convolutional-features-for-multi-label
Repo
Framework