Paper Group ANR 200
MEM_GE: a new maximum entropy method for image reconstruction from solar X-ray visibilities. What is the optimal depth for deep-unfolding architectures at deployment?. Optimizing Black-box Metrics with Adaptive Surrogates. Graph Attentional Autoencoder for Anticancer Hyperfood Prediction. Adversarial Imitation Attack. On the adversarial robustness …
MEM_GE: a new maximum entropy method for image reconstruction from solar X-ray visibilities
| Title | MEM_GE: a new maximum entropy method for image reconstruction from solar X-ray visibilities |
| Authors | Paolo Massa, Richard Schwartz, A Kim Tolbert, Anna Maria Massone, Brian R Dennis, Michele Piana, Federico Benvenuto |
| Abstract | Maximum Entropy is an image reconstruction method conceived to image a sparsely occupied field of view and therefore particularly appropriate to achieve super-resolution effects. Although widely used in image deconvolution, this method has been formulated in radio astronomy for the analysis of observations in the spatial frequency domain, and an Interactive Data Language (IDL) code has been implemented for image reconstruction from solar X-ray Fourier data. However, this code relies on a non-convex formulation of the constrained optimization problem addressed by the Maximum Entropy approach and this sometimes results in unreliable reconstructions characterized by unphysical shrinking effects. This paper introduces a new approach to Maximum Entropy based on the constrained minimization of a convex functional. In the case of observations recorded by the Reuven Ramaty High Energy Solar Spectroscopic Imager (RHESSI), the resulting code provides the same super-resolution effects of the previous algorithm, while working properly also when that code produces unphysical reconstructions. Results are also provided of testing the algorithm with synthetic data simulating observations of the Spectrometer/Telescope for Imaging X-rays (STIX) in Solar Orbiter. The new code is available in the {\em{HESSI}} folder of the Solar SoftWare (SSW)tree. |
| Tasks | Image Deconvolution, Image Reconstruction, Super-Resolution |
| Published | 2020-02-18 |
| URL | https://arxiv.org/abs/2002.07921v1 |
| https://arxiv.org/pdf/2002.07921v1.pdf | |
| PWC | https://paperswithcode.com/paper/mem_ge-a-new-maximum-entropy-method-for-image |
| Repo | |
| Framework | |
What is the optimal depth for deep-unfolding architectures at deployment?
| Title | What is the optimal depth for deep-unfolding architectures at deployment? |
| Authors | Nancy Nayak, Thulasi Tholeti, Muralikrishnan Srinivasan, Sheetal Kalyani |
| Abstract | Recently, many iterative algorithms proposed for various applications such as compressed sensing, MIMO Detection, etc. have been unfolded and presented as deep networks; these networks are shown to produce better results than the algorithms in their iterative forms. However, deep networks are highly sensitive to the hyperparameters chosen. Especially for a deep unfolded network, using more layers may lead to redundancy and hence, excessive computation during deployment. In this work, we consider the problem of determining the optimal number of layers required for such unfolded architectures. We propose a method that treats the networks as experts and measures the relative importance of the expertise provided by layers using a variant of the popular Hedge algorithm. Based on the importance of the different layers, we determine the optimal layers required for deployment. We study the effectiveness of this method by applying it to two recent and popular deep-unfolding architectures, namely DetNet and TISTANet. |
| Tasks | |
| Published | 2020-03-20 |
| URL | https://arxiv.org/abs/2003.09446v1 |
| https://arxiv.org/pdf/2003.09446v1.pdf | |
| PWC | https://paperswithcode.com/paper/what-is-the-optimal-depth-for-deep-unfolding |
| Repo | |
| Framework | |
Optimizing Black-box Metrics with Adaptive Surrogates
| Title | Optimizing Black-box Metrics with Adaptive Surrogates |
| Authors | Qijia Jiang, Olaoluwa Adigun, Harikrishna Narasimhan, Mahdi Milani Fard, Maya Gupta |
| Abstract | We address the problem of training models with black-box and hard-to-optimize metrics by expressing the metric as a monotonic function of a small number of easy-to-optimize surrogates. We pose the training problem as an optimization over a relaxed surrogate space, which we solve by estimating local gradients for the metric and performing inexact convex projections. We analyze gradient estimates based on finite differences and local linear interpolations, and show convergence of our approach under smoothness assumptions with respect to the surrogates. Experimental results on classification and ranking problems verify the proposal performs on par with methods that know the mathematical formulation, and adds notable value when the form of the metric is unknown. |
| Tasks | |
| Published | 2020-02-20 |
| URL | https://arxiv.org/abs/2002.08605v1 |
| https://arxiv.org/pdf/2002.08605v1.pdf | |
| PWC | https://paperswithcode.com/paper/optimizing-black-box-metrics-with-adaptive |
| Repo | |
| Framework | |
Graph Attentional Autoencoder for Anticancer Hyperfood Prediction
| Title | Graph Attentional Autoencoder for Anticancer Hyperfood Prediction |
| Authors | Guadalupe Gonzalez, Shunwang Gong, Ivan Laponogov, Kirill Veselkov, Michael Bronstein |
| Abstract | Recent research efforts have shown the possibility to discover anticancer drug-like molecules in food from their effect on protein-protein interaction networks, opening a potential pathway to disease-beating diet design. We formulate this task as a graph classification problem on which graph neural networks (GNNs) have achieved state-of-the-art results. However, GNNs are difficult to train on sparse low-dimensional features according to our empirical evidence. Here, we present graph augmented features, integrating graph structural information and raw node attributes with varying ratios, to ease the training of networks. We further introduce a novel neural network architecture on graphs, the Graph Attentional Autoencoder (GAA) to predict food compounds with anticancer properties based on perturbed protein networks. We demonstrate that the method outperforms the baseline approach and state-of-the-art graph classification models in this task. |
| Tasks | Graph Classification |
| Published | 2020-01-16 |
| URL | https://arxiv.org/abs/2001.05724v1 |
| https://arxiv.org/pdf/2001.05724v1.pdf | |
| PWC | https://paperswithcode.com/paper/graph-attentional-autoencoder-for-anticancer |
| Repo | |
| Framework | |
Adversarial Imitation Attack
| Title | Adversarial Imitation Attack |
| Authors | Mingyi Zhou, Jing Wu, Yipeng Liu, Xiaolin Huang, Shuaicheng Liu, Xiang Zhang, Ce Zhu |
| Abstract | Deep learning models are known to be vulnerable to adversarial examples. A practical adversarial attack should require as little as possible knowledge of attacked models. Current substitute attacks need pre-trained models to generate adversarial examples and their attack success rates heavily rely on the transferability of adversarial examples. Current score-based and decision-based attacks require lots of queries for the attacked models. In this study, we propose a novel adversarial imitation attack. First, it produces a replica of the attacked model by a two-player game like the generative adversarial networks (GANs). The objective of the generative model is to generate examples that lead the imitation model returning different outputs with the attacked model. The objective of the imitation model is to output the same labels with the attacked model under the same inputs. Then, the adversarial examples generated by the imitation model are utilized to fool the attacked model. Compared with the current substitute attacks, imitation attacks can use less training data to produce a replica of the attacked model and improve the transferability of adversarial examples. Experiments demonstrate that our imitation attack requires less training data than the black-box substitute attacks, but achieves an attack success rate close to the white-box attack on unseen data with no query. |
| Tasks | Adversarial Attack |
| Published | 2020-03-28 |
| URL | https://arxiv.org/abs/2003.12760v2 |
| https://arxiv.org/pdf/2003.12760v2.pdf | |
| PWC | https://paperswithcode.com/paper/adversarial-imitation-attack-1 |
| Repo | |
| Framework | |
On the adversarial robustness of DNNs based on error correcting output codes
| Title | On the adversarial robustness of DNNs based on error correcting output codes |
| Authors | Bowen Zhang, Benedetta Tondi, Mauro Barni |
| Abstract | Adversarial examples represent a great security threat for deep learning systems, pushing researchers to develop suitable defense mechanisms. The use of networks adopting error-correcting output codes (ECOC) has recently been proposed to deal with white-box attacks. In this paper, we carry out an in-depth investigation of the security achieved by the ECOC approach. In contrast to previous findings, our analysis reveals that, when the attack in the white-box framework is carried out properly, the ECOC scheme can be attacked by introducing a rather small perturbation. We do so by considering both the popular adversarial attack proposed by Carlini and Wagner (C&W) and a new variant of C&W attack specifically designed for multi-label classification architectures, like the ECOC-based structure. Experimental results regarding different classification tasks demonstrate that ECOC networks can be successfully attacked by both the original C&W attack and the new attack. |
| Tasks | Adversarial Attack, Multi-Label Classification |
| Published | 2020-03-26 |
| URL | https://arxiv.org/abs/2003.11855v1 |
| https://arxiv.org/pdf/2003.11855v1.pdf | |
| PWC | https://paperswithcode.com/paper/on-the-adversarial-robustness-of-dnns-based |
| Repo | |
| Framework | |
Piecewise linear regressions for approximating distance metrics
| Title | Piecewise linear regressions for approximating distance metrics |
| Authors | Josiah Putman, Lisa Oh, Luyang Zhao, Evan Honnold, Galen Brown, Weifu Wang, Devin Balkcom |
| Abstract | This paper presents a data structure that summarizes distances between configurations across a robot configuration space, using a binary space partition whose cells contain parameters used for a locally linear approximation of the distance function. Querying the data structure is extremely fast, particularly when compared to the graph search required for querying Probabilistic Roadmaps, and memory requirements are promising. The paper explores the use of the data structure constructed for a single robot to provide a heuristic for challenging multi-robot motion planning problems. Potential applications also include the use of remote computation to analyze the space of robot motions, which then might be transmitted on-demand to robots with fewer computational resources. |
| Tasks | Motion Planning |
| Published | 2020-02-27 |
| URL | https://arxiv.org/abs/2002.12466v1 |
| https://arxiv.org/pdf/2002.12466v1.pdf | |
| PWC | https://paperswithcode.com/paper/piecewise-linear-regressions-for |
| Repo | |
| Framework | |
Asymptotic errors for convex penalized linear regression beyond Gaussian matrices
| Title | Asymptotic errors for convex penalized linear regression beyond Gaussian matrices |
| Authors | Cédric Gerbelot, Alia Abbara, Florent Krzakala |
| Abstract | We consider the problem of learning a coefficient vector $x_{0}$ in $R^{N}$ from noisy linear observations $y=Fx_{0}+w$ in $R^{M}$ in the high dimensional limit $M,N$ to infinity with $\alpha=M/N$ fixed. We provide a rigorous derivation of an explicit formula – first conjectured using heuristic methods from statistical physics – for the asymptotic mean squared error obtained by penalized convex regression estimators such as the LASSO or the elastic net, for a class of very generic random matrices corresponding to rotationally invariant data matrices with arbitrary spectrum. The proof is based on a convergence analysis of an oracle version of vector approximate message-passing (oracle-VAMP) and on the properties of its state evolution equations. Our method leverages on and highlights the link between vector approximate message-passing, Douglas-Rachford splitting and proximal descent algorithms, extending previous results obtained with i.i.d. matrices for a large class of problems. We illustrate our results on some concrete examples and show that even though they are asymptotic, our predictions agree remarkably well with numerics even for very moderate sizes. |
| Tasks | |
| Published | 2020-02-11 |
| URL | https://arxiv.org/abs/2002.04372v1 |
| https://arxiv.org/pdf/2002.04372v1.pdf | |
| PWC | https://paperswithcode.com/paper/asymptotic-errors-for-convex-penalized-linear |
| Repo | |
| Framework | |
Frequency-Tuned Universal Adversarial Attacks
| Title | Frequency-Tuned Universal Adversarial Attacks |
| Authors | Yingpeng Deng, Lina J. Karam |
| Abstract | Researchers have shown that the predictions of a convolutional neural network (CNN) for an image set can be severely distorted by one single image-agnostic perturbation, or universal perturbation, usually with an empirically fixed threshold in the spatial domain to restrict its perceivability. However, by considering the human perception, we propose to adopt JND thresholds to guide the perceivability of universal adversarial perturbations. Based on this, we propose a frequency-tuned universal attack method to compute universal perturbations and show that our method can realize a good balance between perceivability and effectiveness in terms of fooling rate by adapting the perturbations to the local frequency content. Compared with existing universal adversarial attack techniques, our frequency-tuned attack method can achieve cutting-edge quantitative results. We demonstrate that our approach can significantly improve the performance of the baseline on both white-box and black-box attacks. |
| Tasks | Adversarial Attack |
| Published | 2020-03-11 |
| URL | https://arxiv.org/abs/2003.05549v1 |
| https://arxiv.org/pdf/2003.05549v1.pdf | |
| PWC | https://paperswithcode.com/paper/frequency-tuned-universal-adversarial-attacks |
| Repo | |
| Framework | |
Pseudo-dimension of quantum circuits
| Title | Pseudo-dimension of quantum circuits |
| Authors | Matthias C. Caro, Ishaun Datta |
| Abstract | We characterize the expressive power of quantum circuits with the pseudo-dimension, a measure of complexity for probabilistic concept classes. We prove pseudo-dimension bounds on the output probability distributions of quantum circuits; the upper bounds are polynomial in circuit depth and number of gates. Using these bounds, we exhibit a class of circuit output states out of which at least one has exponential state complexity, and moreover demonstrate that quantum circuits of known polynomial size and depth are PAC-learnable. |
| Tasks | |
| Published | 2020-02-04 |
| URL | https://arxiv.org/abs/2002.01490v1 |
| https://arxiv.org/pdf/2002.01490v1.pdf | |
| PWC | https://paperswithcode.com/paper/pseudo-dimension-of-quantum-circuits |
| Repo | |
| Framework | |
Using an ensemble color space model to tackle adversarial examples
| Title | Using an ensemble color space model to tackle adversarial examples |
| Authors | Shreyank N Gowda, Chun Yuan |
| Abstract | Minute pixel changes in an image drastically change the prediction that the deep learning model makes. One of the most significant problems that could arise due to this, for instance, is autonomous driving. Many methods have been proposed to combat this with varying amounts of success. We propose a 3 step method for defending such attacks. First, we denoise the image using statistical methods. Second, we show that adopting multiple color spaces in the same model can help us to fight these adversarial attacks further as each color space detects certain features explicit to itself. Finally, the feature maps generated are enlarged and sent back as an input to obtain even smaller features. We show that the proposed model does not need to be trained to defend an particular type of attack and is inherently more robust to black-box, white-box, and grey-box adversarial attack techniques. In particular, the model is 56.12 percent more robust than compared models in case of white box attacks when the models are not subject to adversarial example training. |
| Tasks | Adversarial Attack, Autonomous Driving |
| Published | 2020-03-10 |
| URL | https://arxiv.org/abs/2003.05005v1 |
| https://arxiv.org/pdf/2003.05005v1.pdf | |
| PWC | https://paperswithcode.com/paper/using-an-ensemble-color-space-model-to-tackle |
| Repo | |
| Framework | |
Gradient-based adversarial attacks on categorical sequence models via traversing an embedded world
| Title | Gradient-based adversarial attacks on categorical sequence models via traversing an embedded world |
| Authors | Ivan Fursov, Alexey Zaytsev, Nikita Kluchnikov, Andrey Kravchenko, Evgeny Burnaev |
| Abstract | An adversarial attack paradigm explores various scenarios for vulnerability of machine and especially deep learning models: we can apply minor changes to the model input to force a classifier’s failure for a particular example. Most of the state of the art frameworks focus on adversarial attacks for images and other structured model inputs. The adversarial attacks for categorical sequences can also be harmful if they are successful. However, successful attacks for inputs based on categorical sequences should address the following challenges: (1) non-differentiability of the target function, (2) constraints on transformations of initial sequences, and (3) diversity of possible problems. We handle these challenges using two approaches. The first approach adopts Monte-Carlo methods and allows usage in any scenario, the second approach uses a continuous relaxation of models and target metrics, and thus allows using general state of the art methods on adversarial attacks with little additional effort. Results for money transactions, medical fraud, and NLP datasets suggest the proposed methods generate reasonable adversarial sequences that are close to original ones, but fool machine learning models even for blackbox adversarial attacks. |
| Tasks | Adversarial Attack |
| Published | 2020-03-09 |
| URL | https://arxiv.org/abs/2003.04173v1 |
| https://arxiv.org/pdf/2003.04173v1.pdf | |
| PWC | https://paperswithcode.com/paper/gradient-based-adversarial-attacks-on |
| Repo | |
| Framework | |
Fase-AL – Adaptation of Fast Adaptive Stacking of Ensembles for Supporting Active Learning
| Title | Fase-AL – Adaptation of Fast Adaptive Stacking of Ensembles for Supporting Active Learning |
| Authors | Agustín Alejandro Ortiz-Díaz, Fabiano Baldo, Laura María Palomino Mariño, Alberto Verdecia Cabrera |
| Abstract | Classification algorithms to mine data stream have been extensively studied in recent years. However, a lot of these algorithms are designed for supervised learning which requires labeled instances. Nevertheless, the labeling of the data is costly and time-consuming. Because of this, alternative learning paradigms have been proposed to reduce the cost of the labeling process without significant loss of model performance. Active learning is one of these paradigms, whose main objective is to build classification models that request the lowest possible number of labeled examples achieving adequate levels of accuracy. Therefore, this work presents the FASE-AL algorithm which induces classification models with non-labeled instances using Active Learning. FASE-AL is based on the algorithm Fast Adaptive Stacking of Ensembles (FASE). FASE is an ensemble algorithm that detects and adapts the model when the input data stream has concept drift. FASE-AL was compared with four different strategies of active learning found in the literature. Real and synthetic databases were used in the experiments. The algorithm achieves promising results in terms of the percentage of correctly classified instances. |
| Tasks | Active Learning |
| Published | 2020-01-30 |
| URL | https://arxiv.org/abs/2001.11466v1 |
| https://arxiv.org/pdf/2001.11466v1.pdf | |
| PWC | https://paperswithcode.com/paper/fase-al-adaptation-of-fast-adaptive-stacking |
| Repo | |
| Framework | |
Modelling response to trypophobia trigger using intermediate layers of ImageNet networks
| Title | Modelling response to trypophobia trigger using intermediate layers of ImageNet networks |
| Authors | Piotr Woźnicki, Michał Kuźba, Piotr Migdał |
| Abstract | In this paper, we approach the problem of detecting trypophobia triggers using Convolutional neural networks. We show that standard architectures such as VGG or ResNet are capable of recognizing trypophobia patterns. We also conduct experiments to analyze the nature of this phenomenon. To do that, we dissect the network decreasing the number of its layers and parameters. We prove, that even significantly reduced networks have accuracy above 91% and focus their attention on the trypophobia patterns as presented on the visual explanations. |
| Tasks | |
| Published | 2020-02-19 |
| URL | https://arxiv.org/abs/2002.08490v2 |
| https://arxiv.org/pdf/2002.08490v2.pdf | |
| PWC | https://paperswithcode.com/paper/modelling-response-to-trypophobia-trigger |
| Repo | |
| Framework | |
Statistical aspects of nuclear mass models
| Title | Statistical aspects of nuclear mass models |
| Authors | Vojtech Kejzlar, Léo Neufcourt, Witold Nazarewicz, Paul-Gerhard Reinhard |
| Abstract | We study the information content of nuclear masses from the perspective of global models of nuclear binding energies. To this end, we employ a number of statistical methods and diagnostic tools, including Bayesian calibration, Bayesian model averaging, chi-square correlation analysis, principal component analysis, and empirical coverage probability. Using Bayesian framework, we investigate the structure of the 4-parameter Liquid Drop Model by considering discrepant mass domains for calibration. We then use the chi-square correlation framework to analyze the 14-parameter Skyrme energy density functional calibrated using homogeneous and heterogeneous datasets. We show that a quite dramatic parameter reduction can be achieved in both cases. The advantage of the Bayesian model averaging for improving the uncertainty quantification is demonstrated. The statistical approaches used are pedagogically described; in this context this work can serve as a guide for future applications. |
| Tasks | Calibration |
| Published | 2020-02-11 |
| URL | https://arxiv.org/abs/2002.04151v1 |
| https://arxiv.org/pdf/2002.04151v1.pdf | |
| PWC | https://paperswithcode.com/paper/statistical-aspects-of-nuclear-mass-models |
| Repo | |
| Framework | |
