October 19, 2019

3188 words 15 mins read

Paper Group ANR 118

Attention Fusion Networks: Combining Behavior and E-mail Content to Improve Customer Support. Semiparametric Classification of Forest Graphical Models. A Neural Network Model for Determining the Success or Failure of High-tech Projects Development: A Case of Pharmaceutical industry. Deep Unsupervised Multi-View Detection of Video Game Stream Highli …

Attention Fusion Networks: Combining Behavior and E-mail Content to Improve Customer Support


Title	Attention Fusion Networks: Combining Behavior and E-mail Content to Improve Customer Support
Authors	Stephane Fotso, Philip Spanoudes, Benjamin C. Ponedel, Brian Reynoso, Janet Ko
Abstract	Customer support is a central objective at Square as it helps us build and maintain great relationships with our sellers. In order to provide the best experience, we strive to deliver the most accurate and quasi-instantaneous responses to questions regarding our products. In this work, we introduce the Attention Fusion Network model which combines signals extracted from seller interactions on the Square product ecosystem, along with submitted email questions, to predict the most relevant solution to a seller’s inquiry. We show that the innovative combination of two very different data sources that are rarely used together, using state-of-the-art deep learning systems outperforms, candidate models that are trained only on a single source.
Tasks
Published	2018-11-07
URL	http://arxiv.org/abs/1811.03169v2
PDF	http://arxiv.org/pdf/1811.03169v2.pdf
PWC	https://paperswithcode.com/paper/attention-fusion-networks-combining-behavior
Repo
Framework

Semiparametric Classification of Forest Graphical Models


Title	Semiparametric Classification of Forest Graphical Models
Authors	Mary Frances Dorn, Amit Moscovich, Boaz Nadler, Clifford Spiegelman
Abstract	We propose a new semiparametric approach to binary classification that exploits the modeling flexibility of sparse graphical models. Specifically, we assume that each class can be represented by a forest-structured graphical model. Under this assumption, the optimal classifier is linear in the log of the one- and two-dimensional marginal densities. Our proposed procedure non-parametrically estimates the univariate and bivariate marginal densities, maps each sample to the logarithm of these estimated densities and constructs a linear SVM in the transformed space. We prove convergence of the resulting classifier to an oracle SVM classifier and give finite sample bounds on its excess risk. Experiments with simulated and real data indicate that the resulting classifier is competitive with several popular methods across a range of applications.
Tasks
Published	2018-06-06
URL	http://arxiv.org/abs/1806.01993v1
PDF	http://arxiv.org/pdf/1806.01993v1.pdf
PWC	https://paperswithcode.com/paper/semiparametric-classification-of-forest
Repo
Framework

A Neural Network Model for Determining the Success or Failure of High-tech Projects Development: A Case of Pharmaceutical industry


Title	A Neural Network Model for Determining the Success or Failure of High-tech Projects Development: A Case of Pharmaceutical industry
Authors	Hossein Sabzian, Ehsan Kamrani, Seyyed Mostafa Seyyed Hashemi
Abstract	Financing high-tech projects always entails a great deal of risk. The lack of a systematic method to pinpoint the risk of such projects has been recognized as one of the most salient barriers for evaluating them. So, in order to develop a mechanism for evaluating high-tech projects, an Artificial Neural Network (ANN) has been developed through this study. The structure of this paper encompasses four parts. The first part deals with introducing paper’s whole body. The second part gives a literature review. The collection process of risk related variables and the process of developing a Risk Assessment Index system (RAIS) through Principal Component Analysis (PCA) are those issues that are discussed in the third part. The fourth part particularly deals with pharmaceutical industry. Finally, the fifth part has focused on developing an ANN for pattern recognition of failure or success of high-tech projects. Analysis of model’s results and a final conclusion are also presented in this part.
Tasks
Published	2018-09-04
URL	http://arxiv.org/abs/1809.00927v1
PDF	http://arxiv.org/pdf/1809.00927v1.pdf
PWC	https://paperswithcode.com/paper/a-neural-network-model-for-determining-the
Repo
Framework

Deep Unsupervised Multi-View Detection of Video Game Stream Highlights


Title	Deep Unsupervised Multi-View Detection of Video Game Stream Highlights
Authors	Charles Ringer, Mihalis A. Nicolaou
Abstract	We consider the problem of automatic highlight-detection in video game streams. Currently, the vast majority of highlight-detection systems for games are triggered by the occurrence of hard-coded game events (e.g., score change, end-game), while most advanced tools and techniques are based on detection of highlights via visual analysis of game footage. We argue that in the context of game streaming, events that may constitute highlights are not only dependent on game footage, but also on social signals that are conveyed by the streamer during the play session (e.g., when interacting with viewers, or when commenting and reacting to the game). In this light, we present a multi-view unsupervised deep learning methodology for novelty-based highlight detection. The method jointly analyses both game footage and social signals such as the players facial expressions and speech, and shows promising results for generating highlights on streams of popular games such as Player Unknown’s Battlegrounds.
Tasks
Published	2018-07-25
URL	http://arxiv.org/abs/1807.09715v1
PDF	http://arxiv.org/pdf/1807.09715v1.pdf
PWC	https://paperswithcode.com/paper/deep-unsupervised-multi-view-detection-of
Repo
Framework

Distributed Collaborative Hashing and Its Applications in Ant Financial


Title	Distributed Collaborative Hashing and Its Applications in Ant Financial
Authors	Chaochao Chen, Ziqi Liu, Peilin Zhao, Longfei Li, Jun Zhou, Xiaolong Li
Abstract	Collaborative filtering, especially latent factor model, has been popularly used in personalized recommendation. Latent factor model aims to learn user and item latent factors from user-item historic behaviors. To apply it into real big data scenarios, efficiency becomes the first concern, including offline model training efficiency and online recommendation efficiency. In this paper, we propose a Distributed Collaborative Hashing (DCH) model which can significantly improve both efficiencies. Specifically, we first propose a distributed learning framework, following the state-of-the-art parameter server paradigm, to learn the offline collaborative model. Our model can be learnt efficiently by distributedly computing subgradients in minibatches on workers and updating model parameters on servers asynchronously. We then adopt hashing technique to speedup the online recommendation procedure. Recommendation can be quickly made through exploiting lookup hash tables. We conduct thorough experiments on two real large-scale datasets. The experimental results demonstrate that, comparing with the classic and state-of-the-art (distributed) latent factor models, DCH has comparable performance in terms of recommendation accuracy but has both fast convergence speed in offline model training procedure and realtime efficiency in online recommendation procedure. Furthermore, the encouraging performance of DCH is also shown for several real-world applications in Ant Financial.
Tasks
Published	2018-04-13
URL	http://arxiv.org/abs/1804.04918v3
PDF	http://arxiv.org/pdf/1804.04918v3.pdf
PWC	https://paperswithcode.com/paper/distributed-collaborative-hashing-and-its
Repo
Framework

Active Deep Learning Attacks under Strict Rate Limitations for Online API Calls


Title	Active Deep Learning Attacks under Strict Rate Limitations for Online API Calls
Authors	Yi Shi, Yalin E. Sagduyu, Kemal Davaslioglu, Jason H. Li
Abstract	Machine learning has been applied to a broad range of applications and some of them are available online as application programming interfaces (APIs) with either free (trial) or paid subscriptions. In this paper, we study adversarial machine learning in the form of back-box attacks on online classifier APIs. We start with a deep learning based exploratory (inference) attack, which aims to build a classifier that can provide similar classification results (labels) as the target classifier. To minimize the difference between the labels returned by the inferred classifier and the target classifier, we show that the deep learning based exploratory attack requires a large number of labeled training data samples. These labels can be collected by calling the online API, but usually there is some strict rate limitation on the number of allowed API calls. To mitigate the impact of limited training data, we develop an active learning approach that first builds a classifier based on a small number of API calls and uses this classifier to select samples to further collect their labels. Then, a new classifier is built using more training data samples. This updating process can be repeated multiple times. We show that this active learning approach can build an adversarial classifier with a small statistical difference from the target classifier using only a limited number of training data samples. We further consider evasion and causative (poisoning) attacks based on the inferred classifier that is built by the exploratory attack. Evasion attack determines samples that the target classifier is likely to misclassify, whereas causative attack provides erroneous training data samples to reduce the reliability of the re-trained classifier. The success of these attacks show that adversarial machine learning emerges as a feasible threat in the realistic case with limited training data.
Tasks	Active Learning, Inference Attack
Published	2018-11-05
URL	http://arxiv.org/abs/1811.01811v1
PDF	http://arxiv.org/pdf/1811.01811v1.pdf
PWC	https://paperswithcode.com/paper/active-deep-learning-attacks-under-strict
Repo
Framework

Multi-view Metric Learning in Vector-valued Kernel Spaces


Title	Multi-view Metric Learning in Vector-valued Kernel Spaces
Authors	Riikka Huusari, Hachem Kadri, Cécile Capponi
Abstract	We consider the problem of metric learning for multi-view data and present a novel method for learning within-view as well as between-view metrics in vector-valued kernel spaces, as a way to capture multi-modal structure of the data. We formulate two convex optimization problems to jointly learn the metric and the classifier or regressor in kernel feature spaces. An iterative three-step multi-view metric learning algorithm is derived from the optimization problems. In order to scale the computation to large training sets, a block-wise Nystr{"o}m approximation of the multi-view kernel matrix is introduced. We justify our approach theoretically and experimentally, and show its performance on real-world datasets against relevant state-of-the-art methods.
Tasks	Metric Learning
Published	2018-03-21
URL	http://arxiv.org/abs/1803.07821v1
PDF	http://arxiv.org/pdf/1803.07821v1.pdf
PWC	https://paperswithcode.com/paper/multi-view-metric-learning-in-vector-valued
Repo
Framework

Unsupervised learning by a nonlinear network with Hebbian excitatory and anti-Hebbian inhibitory neurons


Title	Unsupervised learning by a nonlinear network with Hebbian excitatory and anti-Hebbian inhibitory neurons
Authors	H. Sebastian Seung
Abstract	This paper introduces a rate-based nonlinear neural network in which excitatory (E) neurons receive feedforward excitation from sensory (S) neurons, and inhibit each other through disynaptic pathways mediated by inhibitory (I) interneurons. Correlation-based plasticity of disynaptic inhibition serves to incompletely decorrelate E neuron activity, pushing the E neurons to learn distinct sensory features. The plasticity equations additionally contain “extra” terms fostering competition between excitatory synapses converging onto the same postsynaptic neuron and inhibitory synapses diverging from the same presynaptic neuron. The parameters of competition between S$\to$E connections can be adjusted to make learned features look more like “parts” or “wholes.” The parameters of competition between I-E connections can be adjusted to set the typical decorrelatedness and sparsity of E neuron activity. Numerical simulations of unsupervised learning show that relatively few I neurons can be sufficient for achieving good decorrelation, and increasing the number of I neurons makes decorrelation more complete. Excitatory and inhibitory inputs to active E neurons are approximately balanced as a result of learning.
Tasks
Published	2018-12-30
URL	http://arxiv.org/abs/1812.11581v1
PDF	http://arxiv.org/pdf/1812.11581v1.pdf
PWC	https://paperswithcode.com/paper/unsupervised-learning-by-a-nonlinear-network
Repo
Framework

Design of robust H_inf fuzzy output feedback controller for affine nonlinear systems:Fuzzy Lyapunov function approach


Title	Design of robust H_inf fuzzy output feedback controller for affine nonlinear systems:Fuzzy Lyapunov function approach
Authors	Leila Rajabpour, Mokhtar Shasadeghi, Alireza Barzegar
Abstract	In this paper, we propose a new systematic approach based on nonquadratic Lyapunov function and technique of introducing slack matrices, for a class of affine nonlinear systems with disturbance. To achieve the goal, first, the affine nonlinear system is represented via Takagi-Sugeno (T-S) fuzzy bilinear model. Subsequently, the robust H_inf controller is designed based on parallel distributed compensation (PDC) scheme. Then, the stability conditions are derived in terms of linear matrix inequalities (LMIs) by utilizing Lyapunov function. Moreover, some slack matrices are proposed to reduce the conservativeness of the LMI stability conditions. Finally, for illustrating the merits and verifying the effectiveness of the proposed approach, the application of an isothermal continuous stirred tank reactor (CSTR) for Van de Vusse reactor is discussed in details.
Tasks
Published	2018-10-20
URL	http://arxiv.org/abs/1810.08759v1
PDF	http://arxiv.org/pdf/1810.08759v1.pdf
PWC	https://paperswithcode.com/paper/design-of-robust-h_inf-fuzzy-output-feedback
Repo
Framework

Transfer Learning with Neural AutoML


Title	Transfer Learning with Neural AutoML
Authors	Catherine Wong, Neil Houlsby, Yifeng Lu, Andrea Gesmundo
Abstract	We reduce the computational cost of Neural AutoML with transfer learning. AutoML relieves human effort by automating the design of ML algorithms. Neural AutoML has become popular for the design of deep learning architectures, however, this method has a high computation cost. To address this we propose Transfer Neural AutoML that uses knowledge from prior tasks to speed up network design. We extend RL-based architecture search methods to support parallel training on multiple tasks and then transfer the search strategy to new tasks. On language and image classification tasks, Transfer Neural AutoML reduces convergence time over single-task training by over an order of magnitude on many tasks.
Tasks	AutoML, Image Classification, Neural Architecture Search, Transfer Learning
Published	2018-03-07
URL	http://arxiv.org/abs/1803.02780v5
PDF	http://arxiv.org/pdf/1803.02780v5.pdf
PWC	https://paperswithcode.com/paper/transfer-learning-with-neural-automl
Repo
Framework

Deep Learning in Mobile and Wireless Networking: A Survey


Title	Deep Learning in Mobile and Wireless Networking: A Survey
Authors	Chaoyun Zhang, Paul Patras, Hamed Haddadi
Abstract	The rapid uptake of mobile devices and the rising popularity of mobile applications and services pose unprecedented demands on mobile and wireless networking infrastructure. Upcoming 5G systems are evolving to support exploding mobile traffic volumes, agile management of network resource to maximize user experience, and extraction of fine-grained real-time analytics. Fulfilling these tasks is challenging, as mobile environments are increasingly complex, heterogeneous, and evolving. One potential solution is to resort to advanced machine learning techniques to help managing the rise in data volumes and algorithm-driven applications. The recent success of deep learning underpins new and powerful tools that tackle problems in this space. In this paper we bridge the gap between deep learning and mobile and wireless networking research, by presenting a comprehensive survey of the crossovers between the two areas. We first briefly introduce essential background and state-of-the-art in deep learning techniques with potential applications to networking. We then discuss several techniques and platforms that facilitate the efficient deployment of deep learning onto mobile systems. Subsequently, we provide an encyclopedic review of mobile and wireless networking research based on deep learning, which we categorize by different domains. Drawing from our experience, we discuss how to tailor deep learning to mobile environments. We complete this survey by pinpointing current challenges and open future directions for research.
Tasks
Published	2018-03-12
URL	http://arxiv.org/abs/1803.04311v3
PDF	http://arxiv.org/pdf/1803.04311v3.pdf
PWC	https://paperswithcode.com/paper/deep-learning-in-mobile-and-wireless
Repo
Framework

Referenceless Performance Evaluation of Audio Source Separation using Deep Neural Networks


Title	Referenceless Performance Evaluation of Audio Source Separation using Deep Neural Networks
Authors	Emad M. Grais, Hagen Wierstorf, Dominic Ward, Russell Mason, Mark D. Plumbley
Abstract	Current performance evaluation for audio source separation depends on comparing the processed or separated signals with reference signals. Therefore, common performance evaluation toolkits are not applicable to real-world situations where the ground truth audio is unavailable. In this paper, we propose a performance evaluation technique that does not require reference signals in order to assess separation quality. The proposed technique uses a deep neural network (DNN) to map the processed audio into its quality score. Our experiment results show that the DNN is capable of predicting the sources-to-artifacts ratio from the blind source separation evaluation toolkit without the need for reference signals.
Tasks
Published	2018-11-01
URL	http://arxiv.org/abs/1811.00454v1
PDF	http://arxiv.org/pdf/1811.00454v1.pdf
PWC	https://paperswithcode.com/paper/referenceless-performance-evaluation-of-audio
Repo
Framework

Efficient Coarse-to-Fine Non-Local Module for the Detection of Small Objects


Title	Efficient Coarse-to-Fine Non-Local Module for the Detection of Small Objects
Authors	Hila Levi, Shimon Ullman
Abstract	An image is not just a collection of objects, but rather a graph where each object is related to other objects through spatial and semantic relations. Using relational reasoning modules, such as the non-local module \cite{wang2017non}, can therefore improve object detection. Current schemes apply such dedicated modules either to a specific layer of the bottom-up stream, or between already-detected objects. We show that the relational process can be better modeled in a coarse-to-fine manner and present a novel framework, applying a non-local module sequentially to increasing resolution feature maps along the top-down stream. In this way, information can naturally passed from larger objects to smaller related ones. Applying the module to fine feature maps further allows the information to pass between the small objects themselves, exploiting repetitions of instances of the same class. In practice, due to the expensive memory utilization of the non-local module, it is infeasible to apply the module as currently used to high-resolution feature maps. We redesigned the non local module, improved it in terms of memory and number of operations, allowing it to be placed anywhere along the network. We further incorporated relative spatial information into the module, in a manner that can be incorporated into our efficient implementation. We show the effectiveness of our scheme by improving the results of detecting small objects on COCO by 1-2 AP points over Faster and Mask RCNN and by 1 AP over using non-local module on the bottom-up stream.
Tasks	Object Detection, Relational Reasoning
Published	2018-11-29
URL	https://arxiv.org/abs/1811.12152v2
PDF	https://arxiv.org/pdf/1811.12152v2.pdf
PWC	https://paperswithcode.com/paper/efficient-coarse-to-fine-non-local-module-for
Repo
Framework

Facial emotion recognition using min-max similarity classifier


Title	Facial emotion recognition using min-max similarity classifier
Authors	Olga Krestinskaya, Alex Pappachen James
Abstract	Recognition of human emotions from the imaging templates is useful in a wide variety of human-computer interaction and intelligent systems applications. However, the automatic recognition of facial expressions using image template matching techniques suffer from the natural variability with facial features and recording conditions. In spite of the progress achieved in facial emotion recognition in recent years, the effective and computationally simple feature selection and classification technique for emotion recognition is still an open problem. In this paper, we propose an efficient and straightforward facial emotion recognition algorithm to reduce the problem of inter-class pixel mismatch during classification. The proposed method includes the application of pixel normalization to remove intensity offsets followed-up with a Min-Max metric in a nearest neighbor classifier that is capable of suppressing feature outliers. The results indicate an improvement of recognition performance from 92.85% to 98.57% for the proposed Min-Max classification method when tested on JAFFE database. The proposed emotion recognition technique outperforms the existing template matching methods.
Tasks	Emotion Recognition, Feature Selection
Published	2018-01-01
URL	http://arxiv.org/abs/1801.00451v1
PDF	http://arxiv.org/pdf/1801.00451v1.pdf
PWC	https://paperswithcode.com/paper/facial-emotion-recognition-using-min-max
Repo
Framework

Limited Gradient Descent: Learning With Noisy Labels


Title	Limited Gradient Descent: Learning With Noisy Labels
Authors	Yi Sun, Yan Tian, Yiping Xu, Jianxiang Li
Abstract	Label noise may affect the generalization of classifiers, and the effective learning of main patterns from samples with noisy labels is an important challenge. Recent studies have shown that deep neural networks tend to prioritize the learning of simple patterns over the memorization of noise patterns. This suggests a possible method to search for the best generalization that learns the main pattern until the noise begins to be memorized. Traditional approaches often employ a clean validation set to find the best stop timing of learning, i.e., early stopping. However, the generalization performance of such methods relies on the quality of validation sets. Further, in practice, a clean validation set is sometimes difficult to obtain. To solve this problem, we propose a method that can estimate the optimal stopping timing without a clean validation set, called limited gradient descent. We modified the labels of a few samples in a noisy dataset to obtain false labels and to create a reverse pattern. By monitoring the learning progress of the noisy and reverse samples, we can determine the stop timing of learning. In this paper, we also theoretically provide some necessary conditions on learning with noisy labels. Experimental results on CIFAR-10 and CIFAR-100 datasets demonstrate that our approach has a comparable generalization performance to methods relying on a clean validation set. Thus, on the noisy Clothing-1M dataset, our approach surpasses methods that rely on a clean validation set.
Tasks
Published	2018-11-20
URL	https://arxiv.org/abs/1811.08117v4
PDF	https://arxiv.org/pdf/1811.08117v4.pdf
PWC	https://paperswithcode.com/paper/limited-gradient-descent-learning-with-noisy
Repo
Framework