October 16, 2019

2952 words 14 mins read

Paper Group ANR 1126

A novel graph-based model for hybrid recommendations in cold-start scenarios. On an improvement of LASSO by scaling. Sequential Neural Methods for Likelihood-free Inference. Multi-armed Bandits with Compensation. Unsupervised Identification of Study Descriptors in Toxicology Research: An Experimental Study. CT Super-resolution GAN Constrained by th …

A novel graph-based model for hybrid recommendations in cold-start scenarios


Title	A novel graph-based model for hybrid recommendations in cold-start scenarios
Authors	Cesare Bernardis, Maurizio Ferrari Dacrema, Paolo Cremonesi
Abstract	Cold-start is a very common and still open problem in the Recommender Systems literature. Since cold start items do not have any interaction, collaborative algorithms are not applicable. One of the main strategies is to use pure or hybrid content-based approaches, which usually yield to lower recommendation quality than collaborative ones. Some techniques to optimize performance of this type of approaches have been studied in recent past. One of them is called feature weighting, which assigns to every feature a real value, called weight, that estimates its importance. Statistical techniques for feature weighting commonly used in Information Retrieval, like TF-IDF, have been adapted for Recommender Systems, but they often do not provide sufficient quality improvements. More recent approaches, FBSM and LFW, estimate weights by leveraging collaborative information via machine learning, in order to learn the importance of a feature based on other users opinions. This type of models have shown promising results compared to classic statistical analyzes cited previously. We propose a novel graph, feature-based machine learning model to face the cold-start item scenario, learning the relevance of features from probabilities of item-based collaborative filtering algorithms.
Tasks	Information Retrieval, Recommendation Systems
Published	2018-08-31
URL	http://arxiv.org/abs/1808.10664v1
PDF	http://arxiv.org/pdf/1808.10664v1.pdf
PWC	https://paperswithcode.com/paper/a-novel-graph-based-model-for-hybrid
Repo
Framework

On an improvement of LASSO by scaling


Title	On an improvement of LASSO by scaling
Authors	Katsuyuki Hagiwara
Abstract	A sparse modeling is a major topic in machine learning and statistics. LASSO (Least Absolute Shrinkage and Selection Operator) is a popular sparse modeling method while it has been known to yield unexpected large bias especially at a sparse representation. There have been several studies for improving this problem such as the introduction of non-convex regularization terms. The important point is that this bias problem directly affects model selection in applications since a sparse representation cannot be selected by a prediction error based model selection even if it is a good representation. In this article, we considered to improve this problem by introducing a scaling that expands LASSO estimator to compensate excessive shrinkage, thus a large bias in LASSO estimator. We here gave an empirical value for the amount of scaling. There are two advantages of this scaling method as follows. Since the proposed scaling value is calculated by using LASSO estimator, we only need LASSO estimator that is obtained by a fast and stable optimization procedure such as LARS (Least Angle Regression) under LASSO modification or coordinate descent. And, the simplicity of our scaling method enables us to derive SURE (Stein’s Unbiased Risk Estimate) under the modified LASSO estimator with scaling. Our scaling method together with model selection based on SURE is fully empirical and do not need additional hyper-parameters. In a simple numerical example, we verified that our scaling method actually improves LASSO and the SURE based model selection criterion can stably choose an appropriate sparse model.
Tasks	Model Selection
Published	2018-08-22
URL	http://arxiv.org/abs/1808.07260v1
PDF	http://arxiv.org/pdf/1808.07260v1.pdf
PWC	https://paperswithcode.com/paper/on-an-improvement-of-lasso-by-scaling
Repo
Framework

Sequential Neural Methods for Likelihood-free Inference


Title	Sequential Neural Methods for Likelihood-free Inference
Authors	Conor Durkan, George Papamakarios, Iain Murray
Abstract	Likelihood-free inference refers to inference when a likelihood function cannot be explicitly evaluated, which is often the case for models based on simulators. Most of the literature is based on sample-based `Approximate Bayesian Computation’ methods, but recent work suggests that approaches based on deep neural conditional density estimators can obtain state-of-the-art results with fewer simulations. The neural approaches vary in how they choose which simulations to run and what they learn: an approximate posterior or a surrogate likelihood. This work provides some direct controlled comparisons between these choices. \|
Tasks
Published	2018-11-21
URL	http://arxiv.org/abs/1811.08723v1
PDF	http://arxiv.org/pdf/1811.08723v1.pdf
PWC	https://paperswithcode.com/paper/sequential-neural-methods-for-likelihood-free
Repo
Framework

Multi-armed Bandits with Compensation


Title	Multi-armed Bandits with Compensation
Authors	Siwei Wang, Longbo Huang
Abstract	We propose and study the known-compensation multi-arm bandit (KCMAB) problem, where a system controller offers a set of arms to many short-term players for $T$ steps. In each step, one short-term player arrives to the system. Upon arrival, the player aims to select an arm with the current best average reward and receives a stochastic reward associated with the arm. In order to incentivize players to explore other arms, the controller provides a proper payment compensation to players. The objective of the controller is to maximize the total reward collected by players while minimizing the compensation. We first provide a compensation lower bound $\Theta(\sum_i {\Delta_i\log T\over KL_i})$, where $\Delta_i$ and $KL_i$ are the expected reward gap and Kullback-Leibler (KL) divergence between distributions of arm $i$ and the best arm, respectively. We then analyze three algorithms to solve the KCMAB problem, and obtain their regrets and compensations. We show that the algorithms all achieve $O(\log T)$ regret and $O(\log T)$ compensation that match the theoretical lower bound. Finally, we present experimental results to demonstrate the performance of the algorithms.
Tasks	Multi-Armed Bandits
Published	2018-11-05
URL	http://arxiv.org/abs/1811.01715v1
PDF	http://arxiv.org/pdf/1811.01715v1.pdf
PWC	https://paperswithcode.com/paper/multi-armed-bandits-with-compensation
Repo
Framework

Unsupervised Identification of Study Descriptors in Toxicology Research: An Experimental Study


Title	Unsupervised Identification of Study Descriptors in Toxicology Research: An Experimental Study
Authors	Drahomira Herrmannova, Steven R. Young, Robert M. Patton, Christopher G. Stahl, Nicole C. Kleinstreuer, Mary S. Wolfe
Abstract	Identifying and extracting data elements such as study descriptors in publication full texts is a critical yet manual and labor-intensive step required in a number of tasks. In this paper we address the question of identifying data elements in an unsupervised manner. Specifically, provided a set of criteria describing specific study parameters, such as species, route of administration, and dosing regimen, we develop an unsupervised approach to identify text segments (sentences) relevant to the criteria. A binary classifier trained to identify publications that met the criteria performs better when trained on the candidate sentences than when trained on sentences randomly picked from the text, supporting the intuition that our method is able to accurately identify study descriptors.
Tasks
Published	2018-11-03
URL	http://arxiv.org/abs/1811.01183v1
PDF	http://arxiv.org/pdf/1811.01183v1.pdf
PWC	https://paperswithcode.com/paper/unsupervised-identification-of-study
Repo
Framework

CT Super-resolution GAN Constrained by the Identical, Residual, and Cycle Learning Ensemble(GAN-CIRCLE)


Title	CT Super-resolution GAN Constrained by the Identical, Residual, and Cycle Learning Ensemble(GAN-CIRCLE)
Authors	Chenyu You, Guang Li, Yi Zhang, Xiaoliu Zhang, Hongming Shan, Shenghong Ju, Zhen Zhao, Zhuiyang Zhang, Wenxiang Cong, Michael W. Vannier, Punam K. Saha, Ge Wang
Abstract	Computed tomography (CT) is widely used in screening, diagnosis, and image-guided therapy for both clinical and research purposes. Since CT involves ionizing radiation, an overarching thrust of related technical research is development of novel methods enabling ultrahigh quality imaging with fine structural details while reducing the X-ray radiation. In this paper, we present a semi-supervised deep learning approach to accurately recover high-resolution (HR) CT images from low-resolution (LR) counterparts. Specifically, with the generative adversarial network (GAN) as the building block, we enforce the cycle-consistency in terms of the Wasserstein distance to establish a nonlinear end-to-end mapping from noisy LR input images to denoised and deblurred HR outputs. We also include the joint constraints in the loss function to facilitate structural preservation. In this deep imaging process, we incorporate deep convolutional neural network (CNN), residual learning, and network in network techniques for feature extraction and restoration. In contrast to the current trend of increasing network depth and complexity to boost the CT imaging performance, which limit its real-world applications by imposing considerable computational and memory overheads, we apply a parallel $1\times1$ CNN to compress the output of the hidden layer and optimize the number of layers and the number of filters for each convolutional layer. Quantitative and qualitative evaluations demonstrate that our proposed model is accurate, efficient and robust for super-resolution (SR) image restoration from noisy LR input images. In particular, we validate our composite SR networks on three large-scale CT datasets, and obtain promising results as compared to the other state-of-the-art methods.
Tasks	Computed Tomography (CT), Image Restoration, Super-Resolution
Published	2018-08-10
URL	http://arxiv.org/abs/1808.04256v3
PDF	http://arxiv.org/pdf/1808.04256v3.pdf
PWC	https://paperswithcode.com/paper/ct-super-resolution-gan-constrained-by-the
Repo
Framework

Brief survey of Mobility Analyses based on Mobile Phone Datasets


Title	Brief survey of Mobility Analyses based on Mobile Phone Datasets
Authors	Carlos Sarraute, Martin Minnoni
Abstract	This is a brief survey of the research performed by Grandata Labs in collaboration with numerous academic groups around the world on the topic of human mobility. A driving theme in these projects is to use and improve Data Science techniques to understand mobility, as it can be observed through the lens of mobile phone datasets. We describe applications of mobility analyses for urban planning, prediction of data traffic usage, building delay tolerant networks, generating epidemiologic risk maps and measuring the predictability of human mobility.
Tasks
Published	2018-12-03
URL	http://arxiv.org/abs/1812.01077v1
PDF	http://arxiv.org/pdf/1812.01077v1.pdf
PWC	https://paperswithcode.com/paper/brief-survey-of-mobility-analyses-based-on
Repo
Framework

Scalable Structure Learning for Probabilistic Soft Logic


Title	Scalable Structure Learning for Probabilistic Soft Logic
Authors	Varun Embar, Dhanya Sridhar, Golnoosh Farnadi, Lise Getoor
Abstract	Statistical relational frameworks such as Markov logic networks and probabilistic soft logic (PSL) encode model structure with weighted first-order logical clauses. Learning these clauses from data is referred to as structure learning. Structure learning alleviates the manual cost of specifying models. However, this benefit comes with high computational costs; structure learning typically requires an expensive search over the space of clauses which involves repeated optimization of clause weights. In this paper, we propose the first two approaches to structure learning for PSL. We introduce a greedy search-based algorithm and a novel optimization method that trade-off scalability and approximations to the structure learning problem in varying ways. The highly scalable optimization method combines data-driven generation of clauses with a piecewise pseudolikelihood (PPLL) objective that learns model structure by optimizing clause weights only once. We compare both methods across five real-world tasks, showing that PPLL achieves an order of magnitude runtime speedup and AUC gains up to 15% over greedy search.
Tasks
Published	2018-07-03
URL	http://arxiv.org/abs/1807.00973v1
PDF	http://arxiv.org/pdf/1807.00973v1.pdf
PWC	https://paperswithcode.com/paper/scalable-structure-learning-for-probabilistic
Repo
Framework

NU-LiteNet: Mobile Landmark Recognition using Convolutional Neural Networks


Title	NU-LiteNet: Mobile Landmark Recognition using Convolutional Neural Networks
Authors	Chakkrit Termritthikun, Surachet Kanprachar, Paisarn Muneesawang
Abstract	The growth of high-performance mobile devices has resulted in more research into on-device image recognition. The research problems are the latency and accuracy of automatic recognition, which remains obstacles to its real-world usage. Although the recently developed deep neural networks can achieve accuracy comparable to that of a human user, some of them still lack the necessary latency. This paper describes the development of the architecture of a new convolutional neural network model, NU-LiteNet. For this, SqueezeNet was developed to reduce the model size to a degree suitable for smartphones. The model size of NU-LiteNet is therefore 2.6 times smaller than that of SqueezeNet. The recognition accuracy of NU-LiteNet also compared favorably with other recently developed deep neural networks, when experiments were conducted on two standard landmark databases.
Tasks
Published	2018-10-02
URL	http://arxiv.org/abs/1810.01074v1
PDF	http://arxiv.org/pdf/1810.01074v1.pdf
PWC	https://paperswithcode.com/paper/nu-litenet-mobile-landmark-recognition-using
Repo
Framework

Frequency Principle in Deep Learning with General Loss Functions and Its Potential Application


Title	Frequency Principle in Deep Learning with General Loss Functions and Its Potential Application
Authors	Zhi-Qin John Xu
Abstract	Previous studies have shown that deep neural networks (DNNs) with common settings often capture target functions from low to high frequency, which is called Frequency Principle (F-Principle). It has also been shown that F-Principle can provide an understanding to the often observed good generalization ability of DNNs. However, previous studies focused on the loss function of mean square error, while various loss functions are used in practice. In this work, we show that the F-Principle holds for a general loss function (e.g., mean square error, cross entropy, etc.). In addition, DNN’s F-Principle may be applied to develop numerical schemes for solving various problems which would benefit from a fast converging of low frequency. As an example of the potential usage of F-Principle, we apply DNN in solving differential equations, in which conventional methods (e.g., Jacobi method) is usually slow in solving problems due to the convergence from high to low frequency.
Tasks
Published	2018-11-26
URL	http://arxiv.org/abs/1811.10146v1
PDF	http://arxiv.org/pdf/1811.10146v1.pdf
PWC	https://paperswithcode.com/paper/frequency-principle-in-deep-learning-with
Repo
Framework

Dropout-GAN: Learning from a Dynamic Ensemble of Discriminators


Title	Dropout-GAN: Learning from a Dynamic Ensemble of Discriminators
Authors	Gonçalo Mordido, Haojin Yang, Christoph Meinel
Abstract	We propose to incorporate adversarial dropout in generative multi-adversarial networks, by omitting or dropping out, the feedback of each discriminator in the framework with some probability at the end of each batch. Our approach forces the single generator not to constrain its output to satisfy a single discriminator, but, instead, to satisfy a dynamic ensemble of discriminators. We show that this leads to a more generalized generator, promoting variety in the generated samples and avoiding the common mode collapse problem commonly experienced with generative adversarial networks (GANs). We further provide evidence that the proposed framework, named Dropout-GAN, promotes sample diversity both within and across epochs, eliminating mode collapse and stabilizing training.
Tasks
Published	2018-07-30
URL	https://arxiv.org/abs/1807.11346v2
PDF	https://arxiv.org/pdf/1807.11346v2.pdf
PWC	https://paperswithcode.com/paper/dropout-gan-learning-from-a-dynamic-ensemble
Repo
Framework

Comparator Networks


Title	Comparator Networks
Authors	Weidi Xie, Li Shen, Andrew Zisserman
Abstract	The objective of this work is set-based verification, e.g. to decide if two sets of images of a face are of the same person or not. The traditional approach to this problem is to learn to generate a feature vector per image, aggregate them into one vector to represent the set, and then compute the cosine similarity between sets. Instead, we design a neural network architecture that can directly learn set-wise verification. Our contributions are: (i) We propose a Deep Comparator Network (DCN) that can ingest a pair of sets (each may contain a variable number of images) as inputs, and compute a similarity between the pair–this involves attending to multiple discriminative local regions (landmarks), and comparing local descriptors between pairs of faces; (ii) To encourage high-quality representations for each set, internal competition is introduced for recalibration based on the landmark score; (iii) Inspired by image retrieval, a novel hard sample mining regime is proposed to control the sampling process, such that the DCN is complementary to the standard image classification models. Evaluations on the IARPA Janus face recognition benchmarks show that the comparator networks outperform the previous state-of-the-art results by a large margin.
Tasks	Face Recognition, Image Classification, Image Retrieval
Published	2018-07-30
URL	http://arxiv.org/abs/1807.11440v1
PDF	http://arxiv.org/pdf/1807.11440v1.pdf
PWC	https://paperswithcode.com/paper/comparator-networks
Repo
Framework

Photo-unrealistic Image Enhancement for Subject Placement in Outdoor Photography


Title	Photo-unrealistic Image Enhancement for Subject Placement in Outdoor Photography
Authors	Christian Tendyck, Andrew Haddad, Mireille Boutin
Abstract	Camera display reflections are an issue in bright light situations, as they may prevent users from correctly positioning the subject in the picture. We propose a software solution to this problem, which consists in modifying the image in the viewer, in real time. In our solution, the user is seeing a posterized image which roughly represents the contour of the objects. Five enhancement methods are compared in a user study. Our results indicate that the problem considered is a valid one, as users had problems locating landmarks nearly 37% of the time under sunny conditions, and that our proposed enhancement method using contrasting colors is a practical solution to that problem.
Tasks	Image Enhancement
Published	2018-07-17
URL	http://arxiv.org/abs/1807.06196v1
PDF	http://arxiv.org/pdf/1807.06196v1.pdf
PWC	https://paperswithcode.com/paper/photo-unrealistic-image-enhancement-for
Repo
Framework

Deep Comparison: Relation Columns for Few-Shot Learning


Title	Deep Comparison: Relation Columns for Few-Shot Learning
Authors	Xueting Zhang, Flood Sung, Yuting Qiang, Yongxin Yang, Timothy M. Hospedales
Abstract	Few-shot deep learning is a topical challenge area for scaling visual recognition to open-ended growth in the space of categories to recognise. A promising line work towards realising this vision is deep networks that learn to match queries with stored training images. However, methods in this paradigm usually train a deep embedding followed by a single linear classifier. Our insight is that effective general-purpose matching requires discrimination with regards to features at multiple abstraction levels. We therefore propose a new framework termed Deep Comparison Network(DCN) that decomposes embedding learning into a sequence of modules, and pairs each with a relation module. The relation modules compute a non-linear metric to score the match using the corresponding embedding module’s representation. To ensure that all embedding module’s features are used, the relation modules are deeply supervised. Finally generalisation is further improved by a learned noise regulariser. The resulting network achieves state of the art performance on both miniImageNet and tieredImageNet, while retaining the appealing simplicity and efficiency of deep metric learning approaches.
Tasks	Few-Shot Image Classification, Few-Shot Learning, Metric Learning
Published	2018-11-17
URL	http://arxiv.org/abs/1811.07100v2
PDF	http://arxiv.org/pdf/1811.07100v2.pdf
PWC	https://paperswithcode.com/paper/deep-comparison-relation-columns-for-few-shot
Repo
Framework

Imbalanced Ensemble Classifier for learning from imbalanced business school data set


Title	Imbalanced Ensemble Classifier for learning from imbalanced business school data set
Authors	Tanujit Chakraborty
Abstract	Private business schools in India face a common problem of selecting quality students for their MBA programs to achieve the desired placement percentage. Generally, such data sets are biased towards one class, i.e., imbalanced in nature. And learning from the imbalanced dataset is a difficult proposition. This paper proposes an imbalanced ensemble classifier which can handle the imbalanced nature of the dataset and achieves higher accuracy in case of the feature selection (selection of important characteristics of students) cum classification problem (prediction of placements based on the students’ characteristics) for Indian business school dataset. The optimal value of an important model parameter is found. Numerical evidence is also provided using Indian business school dataset to assess the outstanding performance of the proposed classifier.
Tasks	Feature Selection
Published	2018-05-31
URL	http://arxiv.org/abs/1805.12381v2
PDF	http://arxiv.org/pdf/1805.12381v2.pdf
PWC	https://paperswithcode.com/paper/imbalanced-ensemble-classifier-for-learning
Repo
Framework