Paper Group ANR 1101
Dynamical Triangulation Induced by Quantum Walk. Transition Subspace Learning based Least Squares Regression for Image Classification. Joint Detection of Malicious Domains and Infected Clients. SVM-based Deep Stacking Networks. Action Modifiers: Learning from Adverbs in Instructional Videos. Design of optical neural networks with component imprecis …
Dynamical Triangulation Induced by Quantum Walk
| Title | Dynamical Triangulation Induced by Quantum Walk |
| Authors | Quentin Aristote, Nathanaël Eon, Giuseppe Di Molfetta |
| Abstract | We present the single-particle sector of a quantum cellular automaton, namely a quantum walk, on a simple dynamical triangulated $2-$manifold. The triangulation is changed through Pachner moves, induced by the walker density itself, allowing the surface to transform into any topologically equivalent one. This model extends the quantum walk over triangular grid, introduced in a previous work, by one of the authors, whose space-time limit recovers the Dirac equation in (2+1)-dimensions. Numerical simulations show that the number of triangles and the local curvature grow as $t^\alpha e^{-\beta t^2}$, where $\alpha$ and $\beta$ parametrize the way geometry changes upon the local density of the walker, and that, in the long run, flatness emerges. Finally, we also prove that the global behavior of the walker, remains the same under spacetime random fluctuations. |
| Tasks | |
| Published | 2019-07-24 |
| URL | https://arxiv.org/abs/1907.10717v5 |
| https://arxiv.org/pdf/1907.10717v5.pdf | |
| PWC | https://paperswithcode.com/paper/quantum-walk-over-a-triangular-lattice |
| Repo | |
| Framework | |
Transition Subspace Learning based Least Squares Regression for Image Classification
| Title | Transition Subspace Learning based Least Squares Regression for Image Classification |
| Authors | Zhe Chen, Xiao-Jun Wu, Josef Kittler |
| Abstract | Only learning one projection matrix from original samples to the corresponding binary labels is too strict and will consequentlly lose some intrinsic geometric structures of data. In this paper, we propose a novel transition subspace learning based least squares regression (TSL-LSR) model for multicategory image classification. The main idea of TSL-LSR is to learn a transition subspace between the original samples and binary labels to alleviate the problem of overfitting caused by strict projection learning. Moreover, in order to reflect the underlying low-rank structure of transition matrix and learn more discriminative projection matrix, a low-rank constraint is added to the transition subspace. Experimental results on several image datasets demonstrate the effectiveness of the proposed TSL-LSR model in comparison with state-of-the-art algorithms |
| Tasks | Image Classification |
| Published | 2019-05-14 |
| URL | https://arxiv.org/abs/1905.05445v2 |
| https://arxiv.org/pdf/1905.05445v2.pdf | |
| PWC | https://paperswithcode.com/paper/transition-subspace-learning-based-least |
| Repo | |
| Framework | |
Joint Detection of Malicious Domains and Infected Clients
| Title | Joint Detection of Malicious Domains and Infected Clients |
| Authors | Paul Prasse, Rene Knaebel, Lukas Machlica, Tomas Pevny, Tobias Scheffer |
| Abstract | Detection of malware-infected computers and detection of malicious web domains based on their encrypted HTTPS traffic are challenging problems, because only addresses, timestamps, and data volumes are observable. The detection problems are coupled, because infected clients tend to interact with malicious domains. Traffic data can be collected at a large scale, and antivirus tools can be used to identify infected clients in retrospect. Domains, by contrast, have to be labeled individually after forensic analysis. We explore transfer learning based on sluice networks; this allows the detection models to bootstrap each other. In a large-scale experimental study, we find that the model outperforms known reference models and detects previously unknown malware, previously unknown malware families, and previously unknown malicious domains. |
| Tasks | Transfer Learning |
| Published | 2019-06-21 |
| URL | https://arxiv.org/abs/1906.09084v1 |
| https://arxiv.org/pdf/1906.09084v1.pdf | |
| PWC | https://paperswithcode.com/paper/joint-detection-of-malicious-domains-and |
| Repo | |
| Framework | |
SVM-based Deep Stacking Networks
| Title | SVM-based Deep Stacking Networks |
| Authors | Jingyuan Wang, Kai Feng, Junjie Wu |
| Abstract | The deep network model, with the majority built on neural networks, has been proved to be a powerful framework to represent complex data for high performance machine learning. In recent years, more and more studies turn to nonneural network approaches to build diverse deep structures, and the Deep Stacking Network (DSN) model is one of such approaches that uses stacked easy-to-learn blocks to build a parameter-training-parallelizable deep network. In this paper, we propose a novel SVM-based Deep Stacking Network (SVM-DSN), which uses the DSN architecture to organize linear SVM classifiers for deep learning. A BP-like layer tuning scheme is also proposed to ensure holistic and local optimizations of stacked SVMs simultaneously. Some good math properties of SVM, such as the convex optimization, is introduced into the DSN framework by our model. From a global view, SVM-DSN can iteratively extract data representations layer by layer as a deep neural network but with parallelizability, and from a local view, each stacked SVM can converge to its optimal solution and obtain the support vectors, which compared with neural networks could lead to interesting improvements in anti-saturation and interpretability. Experimental results on both image and text data sets demonstrate the excellent performances of SVM-DSN compared with some competitive benchmark models. |
| Tasks | |
| Published | 2019-02-15 |
| URL | http://arxiv.org/abs/1902.05731v1 |
| http://arxiv.org/pdf/1902.05731v1.pdf | |
| PWC | https://paperswithcode.com/paper/svm-based-deep-stacking-networks |
| Repo | |
| Framework | |
Action Modifiers: Learning from Adverbs in Instructional Videos
| Title | Action Modifiers: Learning from Adverbs in Instructional Videos |
| Authors | Hazel Doughty, Ivan Laptev, Walterio Mayol-Cuevas, Dima Damen |
| Abstract | We present a method to learn a representation for adverbs from instructional videos using weak supervision from the accompanying narrations. Key to our method is the fact that the visual representation of the adverb is highly dependant on the action to which it applies, although the same adverb will modify multiple actions in a similar way. For instance, while ‘spread quickly’ and ‘mix quickly’ will look dissimilar, we can learn a common representation that allows us to recognize both, among other actions. We formulate this as an embedding problem, and use scaled dot-product attention to learn from weakly-supervised video narrations. We jointly learn adverbs as invertible transformations operating on the embedding space, so as to add or remove the effect of the adverb. As there is no prior work on weakly supervised learning from adverbs, we gather paired action-adverb annotations from a subset of the HowTo100M dataset for 6 adverbs: quickly/slowly, finely/coarsely, and partially/completely. Our method outperforms all baselines for video-to-adverb retrieval with a performance of 0.719 mAP. We also demonstrate our model’s ability to attend to the relevant video parts in order to determine the adverb for a given action. |
| Tasks | |
| Published | 2019-12-13 |
| URL | https://arxiv.org/abs/1912.06617v3 |
| https://arxiv.org/pdf/1912.06617v3.pdf | |
| PWC | https://paperswithcode.com/paper/action-modifiers-learning-from-adverbs-in |
| Repo | |
| Framework | |
Design of optical neural networks with component imprecisions
| Title | Design of optical neural networks with component imprecisions |
| Authors | Michael Y. -S. Fang, Sasikanth Manipatruni, Casimir Wierzynski, Amir Khosrowshahi, Michael R. DeWeese |
| Abstract | For the benefit of designing scalable, fault resistant optical neural networks (ONNs), we investigate the effects architectural designs have on the ONNs’ robustness to imprecise components. We train two ONNs – one with a more tunable design (GridNet) and one with better fault tolerance (FFTNet) – to classify handwritten digits. When simulated without any imperfections, GridNet yields a better accuracy (~98%) than FFTNet (~95%). However, under a small amount of error in their photonic components, the more fault tolerant FFTNet overtakes GridNet. We further provide thorough quantitative and qualitative analyses of ONNs’ sensitivity to varying levels and types of imprecisions. Our results offer guidelines for the principled design of fault-tolerant ONNs as well as a foundation for further research. |
| Tasks | |
| Published | 2019-12-13 |
| URL | https://arxiv.org/abs/2001.01681v1 |
| https://arxiv.org/pdf/2001.01681v1.pdf | |
| PWC | https://paperswithcode.com/paper/design-of-optical-neural-networks-with |
| Repo | |
| Framework | |
A Survey on Deep Learning-based Architectures for Semantic Segmentation on 2D images
| Title | A Survey on Deep Learning-based Architectures for Semantic Segmentation on 2D images |
| Authors | Irem Ulku, Erdem Akagunduz |
| Abstract | Semantic segmentation is the pixel-wise labelling of an image. Since the problem is defined at the pixel level, determining image class labels only is not acceptable, but localising them at the original image pixel resolution is necessary. Boosted by the extraordinary ability of convolutional neural networks (CNN) in creating semantic, high level and hierarchical image features; excessive numbers of deep learning-based 2D semantic segmentation approaches have been proposed within the last decade. In this survey, we mainly focus on the recent scientific developments in semantic segmentation, specifically on deep learning-based methods using 2D images. We started with an analysis of the public image sets and leaderboards for 2D semantic segmantation, with an overview of the techniques employed in performance evaluation. In examining the evolution of the field, we chronologically categorised the approaches into three main periods, namely pre-and early deep learning era, the fully convolutional era, and the post-FCN era. We technically analysed the solutions put forward in terms of solving the fundamental problems of the field, such as fine-grained localisation and scale invariance. Before drawing our conclusions, we present a table of methods from all mentioned eras, with a brief summary of each approach that explains their contribution to the field. We conclude the survey by discussing the current challenges of the field and to what extent they have been solved. |
| Tasks | Semantic Segmentation |
| Published | 2019-12-21 |
| URL | https://arxiv.org/abs/1912.10230v1 |
| https://arxiv.org/pdf/1912.10230v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-survey-on-deep-learning-based-architectures |
| Repo | |
| Framework | |
Learning Personalized Thermal Preferences via Bayesian Active Learning with Unimodality Constraints
| Title | Learning Personalized Thermal Preferences via Bayesian Active Learning with Unimodality Constraints |
| Authors | Nimish Awalgaonkar, Ilias Bilionis, Xiaoqi Liu, Panagiota Karava, Athanasios Tzempelikos |
| Abstract | Thermal preferences vary from person to person and may change over time. The main objective of this paper is to sequentially pose intelligent queries to occupants in order to optimally learn the indoor air temperature values which maximize their satisfaction. Our central hypothesis is that an occupant’s preference relation over indoor air temperature can be described using a scalar function of these temperatures, which we call the “occupant’s thermal utility function”. Information about an occupant’s preference over these temperatures is available to us through their response to thermal preference queries : “prefer warmer,” “prefer cooler” and “satisfied” which we interpret as statements about the derivative of their utility function, i.e. the utility function is “increasing”, “decreasing” and “constant” respectively. We model this hidden utility function using a Gaussian process prior with built-in unimodality constraint, i.e., the utility function has a unique maximum, and we train this model using Bayesian inference. This permits an expected improvement based selection of next preference query to pose to the occupant, which takes into account both exploration (sampling from areas of high uncertainty) and exploitation (sampling from areas which are likely to offer an improvement over current best observation). We use this framework to sequentially design experiments and illustrate its benefits by showing that it requires drastically fewer observations to learn the maximally preferred temperature values as compared to other methods. This framework is an important step towards the development of intelligent HVAC systems which would be able to respond to occupants’ personalized thermal comfort needs. In order to encourage the use of our PE framework and ensure reproducibility in results, we publish an implementation of our work named GPPrefElicit as an open-source package in Python. |
| Tasks | Active Learning, Bayesian Inference |
| Published | 2019-03-21 |
| URL | http://arxiv.org/abs/1903.09094v2 |
| http://arxiv.org/pdf/1903.09094v2.pdf | |
| PWC | https://paperswithcode.com/paper/learning-personalized-thermal-preferences-via |
| Repo | |
| Framework | |
Vision-based Robotic Grasping from Object Localization, Pose Estimation, Grasp Detection to Motion Planning: A Review
| Title | Vision-based Robotic Grasping from Object Localization, Pose Estimation, Grasp Detection to Motion Planning: A Review |
| Authors | Guoguang Du, Kai Wang, Shiguo Lian |
| Abstract | This paper presents a comprehensive survey on vision-based robotic grasping. We concluded four key tasks during robotic grasping, which are object localization, pose estimation, grasp detection and motion planning. In detail, object localization includes object detection and segmentation methods, pose estimation includes RGB-based and RGB-D-based methods, grasp detection includes traditional methods and deep learning-based methods, motion planning includes analytical methods, imitating learning methods, and reinforcement learning methods. Besides, lots of methods accomplish some of the tasks jointly, such as object-detection-combined 6D pose estimation, grasp detection without pose estimation, end-to-end grasp detection, and end-to-end motion planning. These methods are reviewed elaborately in this survey. What’s more, related datasets are summarized and comparisons between state-of-the-art methods are given for each task. Challenges about robotic grasping are presented, and future directions in addressing these challenges are also pointed out. |
| Tasks | 6D Pose Estimation, 6D Pose Estimation using RGB, Motion Planning, Object Detection, Object Localization, Pose Estimation, Robotic Grasping |
| Published | 2019-05-16 |
| URL | https://arxiv.org/abs/1905.06658v1 |
| https://arxiv.org/pdf/1905.06658v1.pdf | |
| PWC | https://paperswithcode.com/paper/vision-based-robotic-grasping-from-object |
| Repo | |
| Framework | |
Cloudy with high chance of DBMS: A 10-year prediction for Enterprise-Grade ML
| Title | Cloudy with high chance of DBMS: A 10-year prediction for Enterprise-Grade ML |
| Authors | Ashvin Agrawal, Rony Chatterjee, Carlo Curino, Avrilia Floratou, Neha Gowdal, Matteo Interlandi, Alekh Jindal, Kostantinos Karanasos, Subru Krishnan, Brian Kroth, Jyoti Leeka, Kwanghyun Park, Hiren Patel, Olga Poppe, Fotis Psallidas, Raghu Ramakrishnan, Abhishek Roy, Karla Saur, Rathijit Sen, Markus Weimer, Travis Wright, Yiwen Zhu |
| Abstract | Machine learning (ML) has proven itself in high-value web applications such as search ranking and is emerging as a powerful tool in a much broader range of enterprise scenarios including voice recognition and conversational understanding for customer support, autotuning for videoconferencing, intelligent feedback loops in large-scale sysops, manufacturing and autonomous vehicle management, complex financial predictions, just to name a few. Meanwhile, as the value of data is increasingly recognized and monetized, concerns about securing valuable data and risks to individual privacy have been growing. Consequently, rigorous data management has emerged as a key requirement in enterprise settings. How will these trends (ML growing popularity, and stricter data governance) intersect? What are the unmet requirements for applying ML in enterprise settings? What are the technical challenges for the DB community to solve? In this paper, we present our vision of how ML and database systems are likely to come together, and early steps we take towards making this vision a reality. |
| Tasks | |
| Published | 2019-08-30 |
| URL | https://arxiv.org/abs/1909.00084v2 |
| https://arxiv.org/pdf/1909.00084v2.pdf | |
| PWC | https://paperswithcode.com/paper/cloudy-with-high-chance-of-dbms-a-10-year |
| Repo | |
| Framework | |
Adaptive Factorization Network: Learning Adaptive-Order Feature Interactions
| Title | Adaptive Factorization Network: Learning Adaptive-Order Feature Interactions |
| Authors | Weiyu Cheng, Yanyan Shen, Linpeng Huang |
| Abstract | Various factorization-based methods have been proposed to leverage second-order, or higher-order cross features for boosting the performance of predictive models. They generally enumerate all the cross features under a predefined maximum order, and then identify useful feature interactions through model training, which suffer from two drawbacks. First, they have to make a trade-off between the expressiveness of higher-order cross features and the computational cost, resulting in suboptimal predictions. Second, enumerating all the cross features, including irrelevant ones, may introduce noisy feature combinations that degrade model performance. In this work, we propose the Adaptive Factorization Network (AFN), a new model that learns arbitrary-order cross features adaptively from data. The core of AFN is a logarithmic transformation layer to convert the power of each feature in a feature combination into the coefficient to be learned. The experimental results on four real datasets demonstrate the superior predictive performance of AFN against the start-of-the-arts. |
| Tasks | |
| Published | 2019-09-07 |
| URL | https://arxiv.org/abs/1909.03276v1 |
| https://arxiv.org/pdf/1909.03276v1.pdf | |
| PWC | https://paperswithcode.com/paper/adaptive-factorization-network-learning |
| Repo | |
| Framework | |
Dynamic Pricing for Airline Ancillaries with Customer Context
| Title | Dynamic Pricing for Airline Ancillaries with Customer Context |
| Authors | Naman Shukla, Arinbjörn Kolbeinsson, Ken Otwell, Lavanya Marla, Kartik Yellepeddi |
| Abstract | Ancillaries have become a major source of revenue and profitability in the travel industry. Yet, conventional pricing strategies are based on business rules that are poorly optimized and do not respond to changing market conditions. This paper describes the dynamic pricing model developed by Deepair solutions, an AI technology provider for travel suppliers. We present a pricing model that provides dynamic pricing recommendations specific to each customer interaction and optimizes expected revenue per customer. The unique nature of personalized pricing provides the opportunity to search over the market space to find the optimal price-point of each ancillary for each customer, without violating customer privacy. In this paper, we present and compare three approaches for dynamic pricing of ancillaries, with increasing levels of sophistication: (1) a two-stage forecasting and optimization model using a logistic mapping function; (2) a two-stage model that uses a deep neural network for forecasting, coupled with a revenue maximization technique using discrete exhaustive search; (3) a single-stage end-to-end deep neural network that recommends the optimal price. We describe the performance of these models based on both offline and online evaluations. We also measure the real-world business impact of these approaches by deploying them in an A/B test on an airline’s internet booking website. We show that traditional machine learning techniques outperform human rule-based approaches in an online setting by improving conversion by 36% and revenue per offer by 10%. We also provide results for our offline experiments which show that deep learning algorithms outperform traditional machine learning techniques for this problem. Our end-to-end deep learning model is currently being deployed by the airline in their booking system. |
| Tasks | |
| Published | 2019-02-06 |
| URL | http://arxiv.org/abs/1902.02236v1 |
| http://arxiv.org/pdf/1902.02236v1.pdf | |
| PWC | https://paperswithcode.com/paper/dynamic-pricing-for-airline-ancillaries-with |
| Repo | |
| Framework | |
Non-negative Tensor Patch Dictionary Approaches for Image Compression and Deblurring Applications
| Title | Non-negative Tensor Patch Dictionary Approaches for Image Compression and Deblurring Applications |
| Authors | Elizabeth Newman, Misha E. Kilmer |
| Abstract | In recent work (Soltani, Kilmer, Hansen, BIT 2016), an algorithm for non-negative tensor patch dictionary learning in the context of X-ray CT imaging and based on a tensor-tensor product called the $t$-product (Kilmer and Martin, 2011) was presented. Building on that work, in this paper, we use of non-negative tensor patch-based dictionaries trained on other data, such as facial image data, for the purposes of either compression or image deblurring. We begin with an analysis in which we address issues such as suitability of the tensor-based approach relative to a matrix-based approach, dictionary size and patch size to balance computational efficiency and qualitative representations. Next, we develop an algorithm that is capable of recovering non-negative tensor coefficients given a non-negative tensor dictionary. The algorithm is based on a variant of the Modified Residual Norm Steepest Descent method. We show how to augment the algorithm to enforce sparsity in the tensor coefficients, and note that the approach has broader applicability since it can be applied to the matrix case as well. We illustrate the surprising result that dictionaries trained on image data from one class can be successfully used to represent and compress image data from different classes and across different resolutions. Finally, we address the use of non-negative tensor dictionaries in image deblurring. We show that tensor treatment of the deblurring problem coupled with non-negative tensor patch dictionaries can give superior restorations as compared to standard treatment of the non-negativity constrained deblurring problem. |
| Tasks | Deblurring, Dictionary Learning, Image Compression |
| Published | 2019-09-25 |
| URL | https://arxiv.org/abs/1910.00993v1 |
| https://arxiv.org/pdf/1910.00993v1.pdf | |
| PWC | https://paperswithcode.com/paper/non-negative-tensor-patch-dictionary |
| Repo | |
| Framework | |
Assisting human experts in the interpretation of their visual process: A case study on assessing copper surface adhesive potency
| Title | Assisting human experts in the interpretation of their visual process: A case study on assessing copper surface adhesive potency |
| Authors | Tristan Hascoet, Xuejiao Deng, Kiyoto Tai, Mari Sugiyama, Yuji Adachi, Sachiko Nakamura, Yasuo Ariki, Tomoko Hayashi, Tetusya Takiguchi |
| Abstract | Deep Neural Networks are often though to lack interpretability due to the distributed nature of their internal representations. In contrast, humans can generally justify, in natural language, for their answer to a visual question with simple common sense reasoning. However, human introspection abilities have their own limits as one often struggles to justify for the recognition process behind our lowest level feature recognition ability: for instance, it is difficult to precisely explain why a given texture seems more characteristic of the surface of a finger nail rather than a plastic bottle. In this paper, we showcase an application in which deep learning models can actually help human experts justify for their own low-level visual recognition process: We study the problem of assessing the adhesive potency of copper sheets from microscopic pictures of their surface. Although highly trained material experts are able to qualitatively assess the surface adhesive potency, they are often unable to precisely justify for their decision process. We present a model that, under careful design considerations, is able to provide visual clues for human experts to understand and justify for their own recognition process. Not only can our model assist human experts in their interpretation of the surface characteristics, we show how this model can be used to test different hypothesis of the copper surface response to different manufacturing processes. |
| Tasks | Common Sense Reasoning |
| Published | 2019-10-24 |
| URL | https://arxiv.org/abs/1910.11033v1 |
| https://arxiv.org/pdf/1910.11033v1.pdf | |
| PWC | https://paperswithcode.com/paper/assisting-human-experts-in-the-interpretation |
| Repo | |
| Framework | |
Towards Better Generalization: BP-SVRG in Training Deep Neural Networks
| Title | Towards Better Generalization: BP-SVRG in Training Deep Neural Networks |
| Authors | Hao Jin, Dachao Lin, Zhihua Zhang |
| Abstract | Stochastic variance-reduced gradient (SVRG) is a classical optimization method. Although it is theoretically proved to have better convergence performance than stochastic gradient descent (SGD), the generalization performance of SVRG remains open. In this paper we investigate the effects of some training techniques, mini-batching and learning rate decay, on the generalization performance of SVRG, and verify the generalization performance of Batch-SVRG (B-SVRG). In terms of the relationship between optimization and generalization, we believe that the average norm of gradients on each training sample as well as the norm of average gradient indicate how flat the landscape is and how well the model generalizes. Based on empirical observations of such metrics, we perform a sign switch on B-SVRG and derive a practical algorithm, BatchPlus-SVRG (BP-SVRG), which is numerically shown to enjoy better generalization performance than B-SVRG, even SGD in some scenarios of deep neural networks. |
| Tasks | |
| Published | 2019-08-18 |
| URL | https://arxiv.org/abs/1908.06395v1 |
| https://arxiv.org/pdf/1908.06395v1.pdf | |
| PWC | https://paperswithcode.com/paper/towards-better-generalization-bp-svrg-in |
| Repo | |
| Framework | |
