January 29, 2020

3086 words 15 mins read

Paper Group ANR 618

Spectral Overlap and a Comparison of Parameter-Free, Dimensionality Reduction Quality Metrics. Waterfall Atrous Spatial Pooling Architecture for Efficient Semantic Segmentation. A data-driven approach for multiscale elliptic PDEs with random coefficients based on intrinsic dimension reduction. Graph Data on the Web: extend the pivot, don’t reinvent …

Spectral Overlap and a Comparison of Parameter-Free, Dimensionality Reduction Quality Metrics


Title	Spectral Overlap and a Comparison of Parameter-Free, Dimensionality Reduction Quality Metrics
Authors	Jonathan Johannemann, Robert Tibshirani
Abstract	Nonlinear dimensionality reduction methods are a popular tool for data scientists and researchers to visualize complex, high dimensional data. However, while these methods continue to improve and grow in number, it is often difficult to evaluate the quality of a visualization due to a variety of factors such as lack of information about the intrinsic dimension of the data and additional tuning required for many evaluation metrics. In this paper, we seek to provide a systematic comparison of dimensionality reduction quality metrics using datasets where we know the ground truth manifold. We utilize each metric for hyperparameter optimization in popular dimensionality reduction methods used for visualization and provide quantitative metrics to objectively compare visualizations to their original manifold. In our results, we find a few methods that appear to consistently do well and propose the best performer as a benchmark for evaluating dimensionality reduction based visualizations.
Tasks	Dimensionality Reduction, Hyperparameter Optimization
Published	2019-07-03
URL	https://arxiv.org/abs/1907.01974v2
PDF	https://arxiv.org/pdf/1907.01974v2.pdf
PWC	https://paperswithcode.com/paper/spectral-overlap-and-a-comparison-of
Repo
Framework

Waterfall Atrous Spatial Pooling Architecture for Efficient Semantic Segmentation


Title	Waterfall Atrous Spatial Pooling Architecture for Efficient Semantic Segmentation
Authors	Bruno Artacho, Andreas Savakis
Abstract	We propose a new efficient architecture for semantic segmentation, based on a “Waterfall” Atrous Spatial Pooling architecture, that achieves a considerable accuracy increase while decreasing the number of network parameters and memory footprint. The proposed Waterfall architecture leverages the efficiency of progressive filtering in the cascade architecture while maintaining multiscale fields-of-view comparable to spatial pyramid configurations. Additionally, our method does not rely on a postprocessing stage with Conditional Random Fields, which further reduces complexity and required training time. We demonstrate that the Waterfall approach with a ResNet backbone is a robust and efficient architecture for semantic segmentation obtaining state-of-the-art results with significant reduction in the number of parameters for the Pascal VOC dataset and the Cityscapes dataset.
Tasks	Semantic Segmentation
Published	2019-12-06
URL	https://arxiv.org/abs/1912.03183v1
PDF	https://arxiv.org/pdf/1912.03183v1.pdf
PWC	https://paperswithcode.com/paper/waterfall-atrous-spatial-pooling-architecture
Repo
Framework

A data-driven approach for multiscale elliptic PDEs with random coefficients based on intrinsic dimension reduction


Title	A data-driven approach for multiscale elliptic PDEs with random coefficients based on intrinsic dimension reduction
Authors	Sijing Li, Zhiwen Zhang, Hongkai Zhao
Abstract	We propose a data-driven approach to solve multiscale elliptic PDEs with random coefficients based on the intrinsic low dimension structure of the underlying elliptic differential operators. Our method consists of offline and online stages. At the offline stage, a low dimension space and its basis are extracted from the data to achieve significant dimension reduction in the solution space. At the online stage, the extracted basis will be used to solve a new multiscale elliptic PDE efficiently. The existence of low dimension structure is established by showing the high separability of the underlying Green’s functions. Different online construction methods are proposed depending on the problem setup. We provide error analysis based on the sampling error and the truncation threshold in building the data-driven basis. Finally, we present numerical examples to demonstrate the accuracy and efficiency of the proposed method.
Tasks	Dimensionality Reduction
Published	2019-07-01
URL	https://arxiv.org/abs/1907.00806v1
PDF	https://arxiv.org/pdf/1907.00806v1.pdf
PWC	https://paperswithcode.com/paper/a-data-driven-approach-for-multiscale
Repo
Framework

Graph Data on the Web: extend the pivot, don’t reinvent the wheel


Title	Graph Data on the Web: extend the pivot, don’t reinvent the wheel
Authors	Fabien Gandon, Franck Michel, Olivier Corby, Michel Buffa, Andrea Tettamanzi, Catherine Faron Zucker, Elena Cabrio, Serena Villata
Abstract	This article is a collective position paper from the Wimmics research team, expressing our vision of how Web graph data technologies should evolve in the future in order to ensure a high-level of interoperability between the many types of applications that produce and consume graph data. Wimmics stands for Web-Instrumented Man-Machine Interactions, Communities, and Semantics. We are a joint research team between INRIA Sophia Antipolis-M{'e}diterran{'e}e and I3S (CNRS and Universit{'e} C{^o}te d’Azur). Our challenge is to bridge formal semantics and social semantics on the web. Our research areas are graph-oriented knowledge representation, reasoning and operationalization to model and support actors, actions and interactions in web-based epistemic communities. The application of our research is supporting and fostering interactions in online communities and management of their resources. In this position paper, we emphasize the need to extend the semantic Web standard stack to address and fulfill new graph data needs, as well as the importance of remaining compatible with existing recommendations, in particular the RDF stack, to avoid the painful duplication of models, languages, frameworks, etc. The following sections group motivations for different directions of work and collect reasons for the creation of a working group on RDF 2.0 and other recommendations of the RDF family.
Tasks
Published	2019-03-11
URL	http://arxiv.org/abs/1903.04181v1
PDF	http://arxiv.org/pdf/1903.04181v1.pdf
PWC	https://paperswithcode.com/paper/graph-data-on-the-web-extend-the-pivot-dont
Repo
Framework

Deep Neural Network Approach to Forward-Inverse Problems


Title	Deep Neural Network Approach to Forward-Inverse Problems
Authors	Hyeontae Jo, Hwijae Son, Hyung Ju Hwang, Eunheui Kim
Abstract	In this paper, we construct approximated solutions of Differential Equations (DEs) using the Deep Neural Network (DNN). Furthermore, we present an architecture that includes the process of finding model parameters through experimental data, the inverse problem. That is, we provide a unified framework of DNN architecture that approximates an analytic solution and its model parameters simultaneously. The architecture consists of a feed forward DNN with non-linear activation functions depending on DEs, automatic differentiation, reduction of order, and gradient based optimization method. We also prove theoretically that the proposed DNN solution converges to an analytic solution in a suitable function space for fundamental DEs. Finally, we perform numerical experiments to validate the robustness of our simplistic DNN architecture for 1D transport equation, 2D heat equation, 2D wave equation, and the Lotka-Volterra system.
Tasks
Published	2019-07-27
URL	https://arxiv.org/abs/1907.12925v1
PDF	https://arxiv.org/pdf/1907.12925v1.pdf
PWC	https://paperswithcode.com/paper/deep-neural-network-approach-to-forward
Repo
Framework

Open Data Chatbot


Title	Open Data Chatbot
Authors	Sophia Keyner, Vadim Savenkov, Svitlana Vakulenko
Abstract	Recently, chatbots received an increased attention from industry and diverse research communities as a dialogue-based interface providing advanced human-computer interactions. On the other hand, Open Data continues to be an important trend and a potential enabler for government transparency and citizen participation. This paper shows how these two paradigms can be combined to help non-expert users find and discover open government datasets through dialogue.
Tasks	Chatbot
Published	2019-09-09
URL	https://arxiv.org/abs/1909.03653v1
PDF	https://arxiv.org/pdf/1909.03653v1.pdf
PWC	https://paperswithcode.com/paper/open-data-chatbot
Repo
Framework

Detecting Anemia from Retinal Fundus Images


Title	Detecting Anemia from Retinal Fundus Images
Authors	Akinori Mitani, Yun Liu, Abigail Huang, Greg S. Corrado, Lily Peng, Dale R. Webster, Naama Hammel, Avinash V. Varadarajan
Abstract	Despite its high prevalence, anemia is often undetected due to the invasiveness and cost of screening and diagnostic tests. Though some non-invasive approaches have been developed, they are less accurate than invasive methods, resulting in an unmet need for more accurate non-invasive methods. Here, we show that deep learning-based algorithms can detect anemia and quantify several related blood measurements using retinal fundus images both in isolation and in combination with basic metadata such as patient demographics. On a validation dataset of 11,388 patients from the UK Biobank, our algorithms achieved a mean absolute error of 0.63 g/dL (95% confidence interval (CI) 0.62-0.64) in quantifying hemoglobin concentration and an area under receiver operating characteristic curve (AUC) of 0.88 (95% CI 0.86-0.89) in detecting anemia. This work shows the potential of automated non-invasive anemia screening based on fundus images, particularly in diabetic patients, who may have regular retinal imaging and are at increased risk of further morbidity and mortality from anemia.
Tasks
Published	2019-04-12
URL	http://arxiv.org/abs/1904.06435v1
PDF	http://arxiv.org/pdf/1904.06435v1.pdf
PWC	https://paperswithcode.com/paper/detecting-anemia-from-retinal-fundus-images
Repo
Framework

Design Space Exploration via Answer Set Programming Modulo Theories


Title	Design Space Exploration via Answer Set Programming Modulo Theories
Authors	Philipp Wanko
Abstract	The design of embedded systems, that are ubiquitously used in mobile devices and cars, is becoming continuously more complex such that efficient system-level design methods are becoming crucial. My research aims at developing systems that help the designer express the complex design problem in a declarative way and explore the design space to obtain divers sets of solutions with desirable properties. To that end, we employ knowledge representation and reasoning capabilities of ASP in combination with background theories. As a result, for the first time, we proposed a sophisticated methodology that allows for the direct integration of multi-objective optimization of non-linear objectives into ASP. This includes unique results of diverse sub-problems covered in several publications which I will present in this work.
Tasks
Published	2019-05-07
URL	https://arxiv.org/abs/1905.05248v1
PDF	https://arxiv.org/pdf/1905.05248v1.pdf
PWC	https://paperswithcode.com/paper/190505248
Repo
Framework

Adversarial Attack on Skeleton-based Human Action Recognition


Title	Adversarial Attack on Skeleton-based Human Action Recognition
Authors	Jian Liu, Naveed Akhtar, Ajmal Mian
Abstract	Deep learning models achieve impressive performance for skeleton-based human action recognition. However, the robustness of these models to adversarial attacks remains largely unexplored due to their complex spatio-temporal nature that must represent sparse and discrete skeleton joints. This work presents the first adversarial attack on skeleton-based action recognition with graph convolutional networks. The proposed targeted attack, termed Constrained Iterative Attack for Skeleton Actions (CIASA), perturbs joint locations in an action sequence such that the resulting adversarial sequence preserves the temporal coherence, spatial integrity, and the anthropomorphic plausibility of the skeletons. CIASA achieves this feat by satisfying multiple physical constraints, and employing spatial skeleton realignments for the perturbed skeletons along with regularization of the adversarial skeletons with Generative networks. We also explore the possibility of semantically imperceptible localized attacks with CIASA, and succeed in fooling the state-of-the-art skeleton action recognition models with high confidence. CIASA perturbations show high transferability for black-box attacks. We also show that the perturbed skeleton sequences are able to induce adversarial behavior in the RGB videos created with computer graphics. A comprehensive evaluation with NTU and Kinetics datasets ascertains the effectiveness of CIASA for graph-based skeleton action recognition and reveals the imminent threat to the spatio-temporal deep learning tasks in general.
Tasks	Adversarial Attack, Skeleton Based Action Recognition, Temporal Action Localization
Published	2019-09-14
URL	https://arxiv.org/abs/1909.06500v1
PDF	https://arxiv.org/pdf/1909.06500v1.pdf
PWC	https://paperswithcode.com/paper/adversarial-attack-on-skeleton-based-human
Repo
Framework

Kernel embedded nonlinear observational mappings in the variational mapping particle filter


Title	Kernel embedded nonlinear observational mappings in the variational mapping particle filter
Authors	Manuel Pulido, Peter Jan vanLeeuwen, Derek J. Posselt
Abstract	Recently, some works have suggested methods to combine variational probabilistic inference with Monte Carlo sampling. One promising approach is via local optimal transport. In this approach, a gradient steepest descent method based on local optimal transport principles is formulated to transform deterministically point samples from an intermediate density to a posterior density. The local mappings that transform the intermediate densities are embedded in a reproducing kernel Hilbert space (RKHS). This variational mapping method requires the evaluation of the log-posterior density gradient and therefore the adjoint of the observational operator. In this work, we evaluate nonlinear observational mappings in the variational mapping method using two approximations that avoid the adjoint, an ensemble based approximation in which the gradient is approximated by the particle covariances in the state and observational spaces the so-called ensemble space and an RKHS approximation in which the observational mapping is embedded in an RKHS and the gradient is derived there. The approximations are evaluated for highly nonlinear observational operators and in a low-dimensional chaotic dynamical system. The RKHS approximation is shown to be highly successful and superior to the ensemble approximation.
Tasks
Published	2019-01-29
URL	http://arxiv.org/abs/1901.10426v1
PDF	http://arxiv.org/pdf/1901.10426v1.pdf
PWC	https://paperswithcode.com/paper/kernel-embedded-nonlinear-observational
Repo
Framework

An Interpretable Neural Network for Configuring Programmable Wireless Environments


Title	An Interpretable Neural Network for Configuring Programmable Wireless Environments
Authors	Christos Liaskos, Ageliki Tsioliaridou, Shuai Nie, Andreas Pitsillides, Sotiris Ioannidis, Ian Akyildiz
Abstract	Software-defined metasurfaces (SDMs) comprise a dense topology of basic elements called meta-atoms, exerting the highest degree of control over surface currents among intelligent panel technologies. As such, they can transform impinging electromagnetic (EM) waves in complex ways, modifying their direction, power, frequency spectrum, polarity and phase. A well-defined software interface allows for applying such functionalities to waves and inter-networking SDMs, while abstracting the underlying physics. A network of SDMs deployed over objects within an area, such as a floorplan walls, creates programmable wireless environments (PWEs) with fully customizable propagation of waves within them. This work studies the use of machine learning for configuring such environments to the benefit of users within. The methodology consists of modeling wireless propagation as a custom, interpretable, back-propagating neural network, with SDM elements as nodes and their cross-interactions as links. Following a training period the network learns the propagation basics of SDMs and configures them to facilitate the communication of users within their vicinity.
Tasks
Published	2019-05-07
URL	https://arxiv.org/abs/1905.02495v1
PDF	https://arxiv.org/pdf/1905.02495v1.pdf
PWC	https://paperswithcode.com/paper/an-interpretable-neural-network-for
Repo
Framework

Dyna-AIL : Adversarial Imitation Learning by Planning


Title	Dyna-AIL : Adversarial Imitation Learning by Planning
Authors	Vaibhav Saxena, Srinivasan Sivanandan, Pulkit Mathur
Abstract	Adversarial methods for imitation learning have been shown to perform well on various control tasks. However, they require a large number of environment interactions for convergence. In this paper, we propose an end-to-end differentiable adversarial imitation learning algorithm in a Dyna-like framework for switching between model-based planning and model-free learning from expert data. Our results on both discrete and continuous environments show that our approach of using model-based planning along with model-free learning converges to an optimal policy with fewer number of environment interactions in comparison to the state-of-the-art learning methods.
Tasks	Imitation Learning
Published	2019-03-08
URL	http://arxiv.org/abs/1903.03234v1
PDF	http://arxiv.org/pdf/1903.03234v1.pdf
PWC	https://paperswithcode.com/paper/dyna-ail-adversarial-imitation-learning-by
Repo
Framework

Approximating the Ideal Observer and Hotelling Observer for binary signal detection tasks by use of supervised learning methods


Title	Approximating the Ideal Observer and Hotelling Observer for binary signal detection tasks by use of supervised learning methods
Authors	Weimin Zhou, Hua Li, Mark A. Anastasio
Abstract	It is widely accepted that optimization of medical imaging system performance should be guided by task-based measures of image quality (IQ). Task-based measures of IQ quantify the ability of an observer to perform a specific task such as detection or estimation of a signal (e.g., a tumor). For binary signal detection tasks, the Bayesian Ideal Observer (IO) sets an upper limit of observer performance and has been advocated for use in optimizing medical imaging systems and data-acquisition designs. Except in special cases, determination of the IO test statistic is analytically intractable. Markov-chain Monte Carlo (MCMC) techniques can be employed to approximate IO detection performance, but their reported applications have been limited to relatively simple object models. In cases where the IO test statistic is difficult to compute, the Hotelling Observer (HO) can be employed. To compute the HO test statistic, potentially large covariance matrices must be accurately estimated and subsequently inverted, which can present computational challenges. This work investigates supervised learning-based methodologies for approximating the IO and HO test statistics. Convolutional neural networks (CNNs) and single-layer neural networks (SLNNs) are employed to approximate the IO and HO test statistics, respectively. Numerical simulations were conducted for both signal-known-exactly (SKE) and signal-known-statistically (SKS) signal detection tasks. The performances of the supervised learning methods are assessed via receiver operating characteristic (ROC) analysis and the results are compared to those produced by use of traditional numerical methods or analytical calculations when feasible. The potential advantages of the proposed supervised learning approaches for approximating the IO and HO test statistics are discussed.
Tasks
Published	2019-05-15
URL	https://arxiv.org/abs/1905.06330v1
PDF	https://arxiv.org/pdf/1905.06330v1.pdf
PWC	https://paperswithcode.com/paper/approximating-the-ideal-observer-and
Repo
Framework

A Hybrid Approach with Optimization and Metric-based Meta-Learner for Few-Shot Learning


Title	A Hybrid Approach with Optimization and Metric-based Meta-Learner for Few-Shot Learning
Authors	Duo Wang, Yu Cheng, Mo Yu, Xiaoxiao Guo, Tao Zhang
Abstract	Few-shot learning aims to learn classifiers for new classes with only a few training examples per class. Most existing few-shot learning approaches belong to either metric-based meta-learning or optimization-based meta-learning category, both of which have achieved successes in the simplified “$k$-shot $N$-way” image classification settings. Specifically, the optimization-based approaches train a meta-learner to predict the parameters of the task-specific classifiers. The task-specific classifiers are required to be homogeneous-structured to ease the parameter prediction, so the meta-learning approaches could only handle few-shot learning problems where the tasks share a uniform number of classes. The metric-based approaches learn one task-invariant metric for all the tasks. Even though the metric-learning approaches allow different numbers of classes, they require the tasks all coming from a similar domain such that there exists a uniform metric that could work across tasks. In this work, we propose a hybrid meta-learning model called Meta-Metric-Learner which combines the merits of both optimization- and metric-based approaches. Our meta-metric-learning approach consists of two components, a task-specific metric-based learner as a base model, and a meta-learner that learns and specifies the base model. Thus our model is able to handle flexible numbers of classes as well as generate more generalized metrics for classification across tasks. We test our approach in the standard “$k$-shot $N$-way” few-shot learning setting following previous works and a new realistic few-shot setting with flexible class numbers in both single-source form and multi-source forms. Experiments show that our approach can obtain superior performance in all settings.
Tasks	Few-Shot Learning, Image Classification, Meta-Learning, Metric Learning
Published	2019-04-04
URL	https://arxiv.org/abs/1904.03014v2
PDF	https://arxiv.org/pdf/1904.03014v2.pdf
PWC	https://paperswithcode.com/paper/a-hybrid-approach-with-optimization-and
Repo
Framework

Artificial Intelligence Governance and Ethics: Global Perspectives


Title	Artificial Intelligence Governance and Ethics: Global Perspectives
Authors	Angela Daly, Thilo Hagendorff, Li Hui, Monique Mann, Vidushi Marda, Ben Wagner, Wei Wang, Saskia Witteborn
Abstract	Artificial intelligence (AI) is a technology which is increasingly being utilised in society and the economy worldwide, and its implementation is planned to become more prevalent in coming years. AI is increasingly being embedded in our lives, supplementing our pervasive use of digital technologies. But this is being accompanied by disquiet over problematic and dangerous implementations of AI, or indeed, even AI itself deciding to do dangerous and problematic actions, especially in fields such as the military, medicine and criminal justice. These developments have led to concerns about whether and how AI systems adhere, and will adhere to ethical standards. These concerns have stimulated a global conversation on AI ethics, and have resulted in various actors from different countries and sectors issuing ethics and governance initiatives and guidelines for AI. Such developments form the basis for our research in this report, combining our international and interdisciplinary expertise to give an insight into what is happening in Australia, China, Europe, India and the US.
Tasks
Published	2019-06-28
URL	https://arxiv.org/abs/1907.03848v1
PDF	https://arxiv.org/pdf/1907.03848v1.pdf
PWC	https://paperswithcode.com/paper/artificial-intelligence-governance-and-ethics
Repo
Framework