Paper Group ANR 723
Reinforcing Adversarial Robustness using Model Confidence Induced by Adversarial Training. Kiwi - A Minimalist CP Solver. Survey of modern Fault Diagnosis methods in networks. Megapixel Size Image Creation using Generative Adversarial Networks. Regularizing Deep Neural Networks by Noise: Its Interpretation and Optimization. Challenging Language-Dep …
Reinforcing Adversarial Robustness using Model Confidence Induced by Adversarial Training
| Title | Reinforcing Adversarial Robustness using Model Confidence Induced by Adversarial Training |
| Authors | Xi Wu, Uyeong Jang, Jiefeng Chen, Lingjiao Chen, Somesh Jha |
| Abstract | In this paper we study leveraging confidence information induced by adversarial training to reinforce adversarial robustness of a given adversarially trained model. A natural measure of confidence is $\F({\bf x})_\infty$ (i.e. how confident $F$ is about its prediction?). We start by analyzing an adversarial training formulation proposed by Madry et al.. We demonstrate that, under a variety of instantiations, an only somewhat good solution to their objective induces confidence to be a discriminator, which can distinguish between right and wrong model predictions in a neighborhood of a point sampled from the underlying distribution. Based on this, we propose Highly Confident Near Neighbor (${\tt HCNN}$), a framework that combines confidence information and nearest neighbor search, to reinforce adversarial robustness of a base model. We give algorithms in this framework and perform a detailed empirical study. We report encouraging experimental results that support our analysis, and also discuss problems we observed with existing adversarial training. |
| Tasks | |
| Published | 2017-11-21 |
| URL | http://arxiv.org/abs/1711.08001v3 |
| http://arxiv.org/pdf/1711.08001v3.pdf | |
| PWC | https://paperswithcode.com/paper/reinforcing-adversarial-robustness-using |
| Repo | |
| Framework | |
Kiwi - A Minimalist CP Solver
| Title | Kiwi - A Minimalist CP Solver |
| Authors | Renaud Hartert |
| Abstract | Kiwi is a minimalist and extendable Constraint Programming (CP) solver specifically designed for education. The particularities of Kiwi stand in its generic trailing state restoration mechanism and its modulable use of variables. By developing Kiwi, the author does not aim to provide an alternative to full featured constraint solvers but rather to provide readers with a basic architecture that will (hopefully) help them to understand the core mechanisms hidden under the hood of constraint solvers, to develop their own extended constraint solver, or to test innovative ideas. |
| Tasks | |
| Published | 2017-04-28 |
| URL | http://arxiv.org/abs/1705.00047v2 |
| http://arxiv.org/pdf/1705.00047v2.pdf | |
| PWC | https://paperswithcode.com/paper/kiwi-a-minimalist-cp-solver |
| Repo | |
| Framework | |
Survey of modern Fault Diagnosis methods in networks
| Title | Survey of modern Fault Diagnosis methods in networks |
| Authors | Zi Jian Yang, Yong Wang |
| Abstract | With the advent of modern computer networks, fault diagnosis has been a focus of research activity. This paper reviews the history of fault diagnosis in networks and discusses the main methods in information gathering section, information analyzing section and diagnosing and revolving section of fault diagnosis in networks. Emphasis will be placed upon knowledge-based methods with discussing the advantages and shortcomings of the different methods. The survey is concluded with a description of some open problems. |
| Tasks | |
| Published | 2017-02-06 |
| URL | http://arxiv.org/abs/1702.01510v1 |
| http://arxiv.org/pdf/1702.01510v1.pdf | |
| PWC | https://paperswithcode.com/paper/survey-of-modern-fault-diagnosis-methods-in |
| Repo | |
| Framework | |
Megapixel Size Image Creation using Generative Adversarial Networks
| Title | Megapixel Size Image Creation using Generative Adversarial Networks |
| Authors | Marco Marchesi |
| Abstract | Since its appearance, Generative Adversarial Networks (GANs) have received a lot of interest in the AI community. In image generation several projects showed how GANs are able to generate photorealistic images but the results so far did not look adequate for the quality standard of visual media production industry. We present an optimized image generation process based on a Deep Convolutional Generative Adversarial Networks (DCGANs), in order to create photorealistic high-resolution images (up to 1024x1024 pixels). Furthermore, the system was fed with a limited dataset of images, less than two thousand images. All these results give more clue about future exploitation of GANs in Computer Graphics and Visual Effects. |
| Tasks | Image Generation |
| Published | 2017-05-31 |
| URL | http://arxiv.org/abs/1706.00082v1 |
| http://arxiv.org/pdf/1706.00082v1.pdf | |
| PWC | https://paperswithcode.com/paper/megapixel-size-image-creation-using |
| Repo | |
| Framework | |
Regularizing Deep Neural Networks by Noise: Its Interpretation and Optimization
| Title | Regularizing Deep Neural Networks by Noise: Its Interpretation and Optimization |
| Authors | Hyeonwoo Noh, Tackgeun You, Jonghwan Mun, Bohyung Han |
| Abstract | Overfitting is one of the most critical challenges in deep neural networks, and there are various types of regularization methods to improve generalization performance. Injecting noises to hidden units during training, e.g., dropout, is known as a successful regularizer, but it is still not clear enough why such training techniques work well in practice and how we can maximize their benefit in the presence of two conflicting objectives—optimizing to true data distribution and preventing overfitting by regularization. This paper addresses the above issues by 1) interpreting that the conventional training methods with regularization by noise injection optimize the lower bound of the true objective and 2) proposing a technique to achieve a tighter lower bound using multiple noise samples per training example in a stochastic gradient descent iteration. We demonstrate the effectiveness of our idea in several computer vision applications. |
| Tasks | |
| Published | 2017-10-14 |
| URL | http://arxiv.org/abs/1710.05179v2 |
| http://arxiv.org/pdf/1710.05179v2.pdf | |
| PWC | https://paperswithcode.com/paper/regularizing-deep-neural-networks-by-noise |
| Repo | |
| Framework | |
Challenging Language-Dependent Segmentation for Arabic: An Application to Machine Translation and Part-of-Speech Tagging
| Title | Challenging Language-Dependent Segmentation for Arabic: An Application to Machine Translation and Part-of-Speech Tagging |
| Authors | Hassan Sajjad, Fahim Dalvi, Nadir Durrani, Ahmed Abdelali, Yonatan Belinkov, Stephan Vogel |
| Abstract | Word segmentation plays a pivotal role in improving any Arabic NLP application. Therefore, a lot of research has been spent in improving its accuracy. Off-the-shelf tools, however, are: i) complicated to use and ii) domain/dialect dependent. We explore three language-independent alternatives to morphological segmentation using: i) data-driven sub-word units, ii) characters as a unit of learning, and iii) word embeddings learned using a character CNN (Convolution Neural Network). On the tasks of Machine Translation and POS tagging, we found these methods to achieve close to, and occasionally surpass state-of-the-art performance. In our analysis, we show that a neural machine translation system is sensitive to the ratio of source and target tokens, and a ratio close to 1 or greater, gives optimal performance. |
| Tasks | Machine Translation, Part-Of-Speech Tagging, Word Embeddings |
| Published | 2017-09-02 |
| URL | http://arxiv.org/abs/1709.00616v1 |
| http://arxiv.org/pdf/1709.00616v1.pdf | |
| PWC | https://paperswithcode.com/paper/challenging-language-dependent-segmentation |
| Repo | |
| Framework | |
A Distributed Approach for Networked Flying Platform Association with Small Cells in 5G+ Networks
| Title | A Distributed Approach for Networked Flying Platform Association with Small Cells in 5G+ Networks |
| Authors | Syed Awais Wahab Shah, Tamer Khattab, Muhammad Zeeshan Shakir, Mazen Omar Hasna |
| Abstract | The densification of small-cell base stations in a 5G architecture is a promising approach to enhance the coverage area and facilitate the ever increasing capacity demand of end users. However, the bottleneck is an intelligent management of a backhaul/fronthaul network for these small-cell base stations. This involves efficient association and placement of the backhaul hubs that connects these small-cells with the core network. Terrestrial hubs suffer from an inefficient non line of sight link limitations and unavailability of a proper infrastructure in an urban area. Seeing the popularity of flying platforms, we employ here an idea of using networked flying platform (NFP) such as unmanned aerial vehicles (UAVs), drones, unmanned balloons flying at different altitudes, as aerial backhaul hubs. The association problem of these NFP-hubs and small-cell base stations is formulated considering backhaul link and NFP related limitations such as maximum number of supported links and bandwidth. Then, this paper presents an efficient and distributed solution of the designed problem, which performs a greedy search in order to maximize the sum rate of the overall network. A favorable performance is observed via a numerical comparison of our proposed method with optimal exhaustive search algorithm in terms of sum rate and run-time speed. |
| Tasks | |
| Published | 2017-04-21 |
| URL | http://arxiv.org/abs/1705.03304v1 |
| http://arxiv.org/pdf/1705.03304v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-distributed-approach-for-networked-flying |
| Repo | |
| Framework | |
Semantic 3D Reconstruction with Finite Element Bases
| Title | Semantic 3D Reconstruction with Finite Element Bases |
| Authors | Audrey Richard, Christoph Vogel, Maros Blaha, Thomas Pock, Konrad Schindler |
| Abstract | We propose a novel framework for the discretisation of multi-label problems on arbitrary, continuous domains. Our work bridges the gap between general FEM discretisations, and labeling problems that arise in a variety of computer vision tasks, including for instance those derived from the generalised Potts model. Starting from the popular formulation of labeling as a convex relaxation by functional lifting, we show that FEM discretisation is valid for the most general case, where the regulariser is anisotropic and non-metric. While our findings are generic and applicable to different vision problems, we demonstrate their practical implementation in the context of semantic 3D reconstruction, where such regularisers have proved particularly beneficial. The proposed FEM approach leads to a smaller memory footprint as well as faster computation, and it constitutes a very simple way to enable variable, adaptive resolution within the same model. |
| Tasks | 3D Reconstruction |
| Published | 2017-10-04 |
| URL | http://arxiv.org/abs/1710.01749v1 |
| http://arxiv.org/pdf/1710.01749v1.pdf | |
| PWC | https://paperswithcode.com/paper/semantic-3d-reconstruction-with-finite |
| Repo | |
| Framework | |
Unified Backpropagation for Multi-Objective Deep Learning
| Title | Unified Backpropagation for Multi-Objective Deep Learning |
| Authors | Arash Shahriari |
| Abstract | A common practice in most of deep convolutional neural architectures is to employ fully-connected layers followed by Softmax activation to minimize cross-entropy loss for the sake of classification. Recent studies show that substitution or addition of the Softmax objective to the cost functions of support vector machines or linear discriminant analysis is highly beneficial to improve the classification performance in hybrid neural networks. We propose a novel paradigm to link the optimization of several hybrid objectives through unified backpropagation. This highly alleviates the burden of extensive boosting for independent objective functions or complex formulation of multiobjective gradients. Hybrid loss functions are linked by basic probability assignment from evidence theory. We conduct our experiments for a variety of scenarios and standard datasets to evaluate the advantage of our proposed unification approach to deliver consistent improvements into the classification performance of deep convolutional neural networks. |
| Tasks | |
| Published | 2017-10-20 |
| URL | http://arxiv.org/abs/1710.07438v1 |
| http://arxiv.org/pdf/1710.07438v1.pdf | |
| PWC | https://paperswithcode.com/paper/unified-backpropagation-for-multi-objective |
| Repo | |
| Framework | |
Online Multilinear Dictionary Learning
| Title | Online Multilinear Dictionary Learning |
| Authors | Thiernithi Variddhisai, Danilo Mandic |
| Abstract | A method for online tensor dictionary learning is proposed. With the assumption of separable dictionaries, tensor contraction is used to diminish a $N$-way model of $\mathcal{O}\left(L^N\right)$ into a simple matrix equation of $\mathcal{O}\left(NL^2\right)$ with a real-time capability. To avoid numerical instability due to inversion of sparse matrix, a class of stochastic gradient with memory is formulated via a least-square solution to guarantee convergence and robustness. Both gradient descent with exact line search and Newton’s method are discussed and realized. Extensions onto how to deal with bad initialization and outliers are also explained in detail. Experiments on two synthetic signals confirms an impressive performance of our proposed method. |
| Tasks | Dictionary Learning |
| Published | 2017-03-07 |
| URL | https://arxiv.org/abs/1703.02492v5 |
| https://arxiv.org/pdf/1703.02492v5.pdf | |
| PWC | https://paperswithcode.com/paper/online-multilinear-dictionary-learning-for |
| Repo | |
| Framework | |
Recommendations for Marketing Campaigns in Telecommunication Business based on the footprint analysis
| Title | Recommendations for Marketing Campaigns in Telecommunication Business based on the footprint analysis |
| Authors | J. Sidorova, L. Skold, O. Rosander, L. Lundberg |
| Abstract | A major investment made by a telecom operator goes into the infrastructure and its maintenance, while business revenues are proportional to how big and good the customer base is. We present a data-driven analytic strategy based on combinatorial optimization and analysis of historical data. The data cover historical mobility of the users in one region of Sweden during a week. Applying the proposed method to the case study, we have identified the optimal proportion of geo-demographic segments in the customer base, developed a functionality to assess the potential of a planned marketing campaign, and explored the problem of an optimal number and types of the geo-demographic segments to target through marketing campaigns. With the help of fuzzy logic, the conclusions of data analysis are automatically translated into comprehensible recommendations in a natural language. |
| Tasks | Combinatorial Optimization |
| Published | 2017-06-13 |
| URL | http://arxiv.org/abs/1706.03944v1 |
| http://arxiv.org/pdf/1706.03944v1.pdf | |
| PWC | https://paperswithcode.com/paper/recommendations-for-marketing-campaigns-in |
| Repo | |
| Framework | |
Session Analysis using Plan Recognition
| Title | Session Analysis using Plan Recognition |
| Authors | Reuth Mirsky, Ya’akov Gal, David Tolpin |
| Abstract | This paper presents preliminary results of our work with a major financial company, where we try to use methods of plan recognition in order to investigate the interactions of a costumer with the company’s online interface. In this paper, we present the first steps of integrating a plan recognition algorithm in a real-world application for detecting and analyzing the interactions of a costumer. It uses a novel approach for plan recognition from bare-bone UI data, which reasons about the plan library at the lowest recognition level in order to define the relevancy of actions in our domain, and then uses it to perform plan recognition. We present preliminary results of inference on three different use-cases modeled by domain experts from the company, and show that this approach manages to decrease the overload of information required from an analyst to evaluate a costumer’s session - whether this is a malicious or benign session, whether the intended tasks were completed, and if not - what actions are expected next. |
| Tasks | |
| Published | 2017-06-20 |
| URL | http://arxiv.org/abs/1706.06328v1 |
| http://arxiv.org/pdf/1706.06328v1.pdf | |
| PWC | https://paperswithcode.com/paper/session-analysis-using-plan-recognition |
| Repo | |
| Framework | |
Un résultat intrigant en commande sans modèle
| Title | Un résultat intrigant en commande sans modèle |
| Authors | Cédric Join, Emmanuel Delaleau, Michel Fliess, Claude H. Moog |
| Abstract | An elementary mathematical example proves, thanks to the Routh-Hurwitz criterion, a result that is intriguing with respect to today’s practical understanding of model-free control, i.e., an “intelligent” proportional controller (iP) may turn to be more difficult to tune than an intelligent proportional-derivative one (iPD). The vast superiority of iPDs when compared to classic PIDs is shown via computer simulations. The introduction as well as the conclusion analyse model-free control in the light of recent advances. |
| Tasks | |
| Published | 2017-11-08 |
| URL | http://arxiv.org/abs/1711.02877v1 |
| http://arxiv.org/pdf/1711.02877v1.pdf | |
| PWC | https://paperswithcode.com/paper/un-resultat-intrigant-en-commande-sans-modele |
| Repo | |
| Framework | |
Deep Convolutional Neural Networks for Anomaly Event Classification on Distributed Systems
| Title | Deep Convolutional Neural Networks for Anomaly Event Classification on Distributed Systems |
| Authors | Jiechao Cheng, Rui Ren, Lei Wang, Jianfeng Zhan |
| Abstract | The increasing popularity of server usage has brought a plenty of anomaly log events, which have threatened a vast collection of machines. Recognizing and categorizing the anomalous events thereby is a much salient work for our systems, especially the ones generate the massive amount of data and harness it for technology value creation and business development. To assist in focusing on the classification and the prediction of anomaly events, and gaining critical insights from system event records, we propose a novel log preprocessing method which is very effective to filter abundant information and retain critical characteristics. Additionally, a competitive approach for automated classification of anomalous events detected from the distributed system logs with the state-of-the-art deep (Convolutional Neural Network) architectures is proposed in this paper. We measure a series of deep CNN algorithms with varied hyper-parameter combinations by using standard evaluation metrics, the results of our study reveals the advantages and potential capabilities of the proposed deep CNN models for anomaly event classification tasks on real-world systems. The optimal classification precision of our approach is 98.14%, which surpasses the popular traditional machine learning methods. |
| Tasks | |
| Published | 2017-10-25 |
| URL | http://arxiv.org/abs/1710.09052v2 |
| http://arxiv.org/pdf/1710.09052v2.pdf | |
| PWC | https://paperswithcode.com/paper/deep-convolutional-neural-networks-for-2 |
| Repo | |
| Framework | |
From Common to Special: When Multi-Attribute Learning Meets Personalized Opinions
| Title | From Common to Special: When Multi-Attribute Learning Meets Personalized Opinions |
| Authors | Zhiyong Yang, Qianqian Xu, Xiaochun Cao, Qingming Huang |
| Abstract | Visual attributes, which refer to human-labeled semantic annotations, have gained increasing popularity in a wide range of real world applications. Generally, the existing attribute learning methods fall into two categories: one focuses on learning user-specific labels separately for different attributes, while the other one focuses on learning crowd-sourced global labels jointly for multiple attributes. However, both categories ignore the joint effect of the two mentioned factors: the personal diversity with respect to the global consensus; and the intrinsic correlation among multiple attributes. To overcome this challenge, we propose a novel model to learn user-specific predictors across multiple attributes. In our proposed model, the diversity of personalized opinions and the intrinsic relationship among multiple attributes are unified in a common-to-special manner. To this end, we adopt a three-component decomposition. Specifically, our model integrates a common cognition factor, an attribute-specific bias factor and a user-specific bias factor. Meanwhile Lasso and group Lasso penalties are adopted to leverage efficient feature selection. Furthermore, theoretical analysis is conducted to show that our proposed method could reach reasonable performance. Eventually, the empirical study carried out in this paper demonstrates the effectiveness of our proposed method. |
| Tasks | Feature Selection |
| Published | 2017-11-18 |
| URL | http://arxiv.org/abs/1711.06867v2 |
| http://arxiv.org/pdf/1711.06867v2.pdf | |
| PWC | https://paperswithcode.com/paper/from-common-to-special-when-multi-attribute |
| Repo | |
| Framework | |
