July 27, 2019

2871 words 14 mins read

Paper Group ANR 650

Subgroup Identification and Interpretation with Bayesian Nonparametric Models in Health Care Claims Data. Direction-Aware Semi-Dense SLAM. Zero-Shot Learning by Generating Pseudo Feature Representations. Spectrally-normalized margin bounds for neural networks. Learning Efficient Image Representation for Person Re-Identification. Optimistic Robust O …

Subgroup Identification and Interpretation with Bayesian Nonparametric Models in Health Care Claims Data


Title	Subgroup Identification and Interpretation with Bayesian Nonparametric Models in Health Care Claims Data
Authors	Christoph Kurz, Laura Hatfield
Abstract	Inpatient care is a large share of total health care spending, making analysis of inpatient utilization patterns an important part of understanding what drives health care spending growth. Common features of inpatient utilization measures include zero inflation, over-dispersion, and skewness, all of which complicate statistical modeling. Mixture modeling is a popular approach that can accommodate these features of health care utilization data. In this work, we add a nonparametric clustering component to such models. Our fully Bayesian model framework allows for an unknown number of mixing components, so that the data determine the number of mixture components. When we apply the modeling framework to data on hospital lengths of stay for patients with lung cancer, we find distinct subgroups of patients with differences in means and variances of hospital days, health and treatment covariates, and relationships between covariates and length of stay.
Tasks
Published	2017-11-20
URL	http://arxiv.org/abs/1711.07527v1
PDF	http://arxiv.org/pdf/1711.07527v1.pdf
PWC	https://paperswithcode.com/paper/subgroup-identification-and-interpretation
Repo
Framework

Direction-Aware Semi-Dense SLAM


Title	Direction-Aware Semi-Dense SLAM
Authors	Julian Straub, Randi Cabezas, John Leonard, John W. Fisher III
Abstract	To aide simultaneous localization and mapping (SLAM), future perception systems will incorporate forms of scene understanding. In a step towards fully integrated probabilistic geometric scene understanding, localization and mapping we propose the first direction-aware semi-dense SLAM system. It jointly infers the directional Stata Center World (SCW) segmentation and a surfel-based semi-dense map while performing real-time camera tracking. The joint SCW map model connects a scene-wide Bayesian nonparametric Dirichlet Process von-Mises-Fisher mixture model (DP-vMF) prior on surfel orientations with the local surfel locations via a conditional random field (CRF). Camera tracking leverages the SCW segmentation to improve efficiency via guided observation selection. Results demonstrate improved SLAM accuracy and tracking efficiency at state of the art performance.
Tasks	Scene Understanding, Simultaneous Localization and Mapping
Published	2017-09-18
URL	http://arxiv.org/abs/1709.05774v1
PDF	http://arxiv.org/pdf/1709.05774v1.pdf
PWC	https://paperswithcode.com/paper/direction-aware-semi-dense-slam
Repo
Framework

Zero-Shot Learning by Generating Pseudo Feature Representations


Title	Zero-Shot Learning by Generating Pseudo Feature Representations
Authors	Jiang Lu, Jin Li, Ziang Yan, Changshui Zhang
Abstract	Zero-shot learning (ZSL) is a challenging task aiming at recognizing novel classes without any training instances. In this paper we present a simple but high-performance ZSL approach by generating pseudo feature representations (GPFR). Given the dataset of seen classes and side information of unseen classes (e.g. attributes), we synthesize feature-level pseudo representations for novel concepts, which allows us access to the formulation of unseen class predictor. Firstly we design a Joint Attribute Feature Extractor (JAFE) to acquire understandings about attributes, then construct a cognitive repository of attributes filtered by confidence margins, and finally generate pseudo feature representations using a probability based sampling strategy to facilitate subsequent training process of class predictor. We demonstrate the effectiveness in ZSL settings and the extensibility in supervised recognition scenario of our method on a synthetic colored MNIST dataset (C-MNIST). For several popular ZSL benchmark datasets, our approach also shows compelling results on zero-shot recognition task, especially leading to tremendous improvement to state-of-the-art mAP on zero-shot retrieval task.
Tasks	Zero-Shot Learning
Published	2017-03-19
URL	http://arxiv.org/abs/1703.06389v1
PDF	http://arxiv.org/pdf/1703.06389v1.pdf
PWC	https://paperswithcode.com/paper/zero-shot-learning-by-generating-pseudo
Repo
Framework

Spectrally-normalized margin bounds for neural networks


Title	Spectrally-normalized margin bounds for neural networks
Authors	Peter Bartlett, Dylan J. Foster, Matus Telgarsky
Abstract	This paper presents a margin-based multiclass generalization bound for neural networks that scales with their margin-normalized “spectral complexity”: their Lipschitz constant, meaning the product of the spectral norms of the weight matrices, times a certain correction factor. This bound is empirically investigated for a standard AlexNet network trained with SGD on the mnist and cifar10 datasets, with both original and random labels; the bound, the Lipschitz constants, and the excess risks are all in direct correlation, suggesting both that SGD selects predictors whose complexity scales with the difficulty of the learning task, and secondly that the presented bound is sensitive to this complexity.
Tasks
Published	2017-06-26
URL	http://arxiv.org/abs/1706.08498v2
PDF	http://arxiv.org/pdf/1706.08498v2.pdf
PWC	https://paperswithcode.com/paper/spectrally-normalized-margin-bounds-for
Repo
Framework

Learning Efficient Image Representation for Person Re-Identification


Title	Learning Efficient Image Representation for Person Re-Identification
Authors	Yang Yang, Shengcai Liao, Zhen Lei, Stan Z. Li
Abstract	Color names based image representation is successfully used in person re-identification, due to the advantages of being compact, intuitively understandable as well as being robust to photometric variance. However, there exists the diversity between underlying distribution of color names’ RGB values and that of image pixels’ RGB values, which may lead to inaccuracy when directly comparing them in Euclidean space. In this paper, we propose a new method named soft Gaussian mapping (SGM) to address this problem. We model the discrepancies between color names and pixels using a Gaussian and utilize the inverse of covariance matrix to bridge the gap between them. Based on SGM, an image could be converted to several soft Gaussian maps. In each soft Gaussian map, we further seek to establish stable and robust descriptors within a local region through a max pooling operation. Then, a robust image representation based on color names is obtained by concatenating the statistical descriptors in each stripe. When labeled data are available, one discriminative subspace projection matrix is learned to build efficient representations of an image via cross-view coupling learning. Experiments on the public datasets - VIPeR, PRID450S and CUHK03, demonstrate the effectiveness of our method.
Tasks	Person Re-Identification
Published	2017-07-07
URL	http://arxiv.org/abs/1707.02319v1
PDF	http://arxiv.org/pdf/1707.02319v1.pdf
PWC	https://paperswithcode.com/paper/learning-efficient-image-representation-for
Repo
Framework

Optimistic Robust Optimization With Applications To Machine Learning


Title	Optimistic Robust Optimization With Applications To Machine Learning
Authors	Matthew Norton, Akiko Takeda, Alexander Mafusalov
Abstract	Robust Optimization has traditionally taken a pessimistic, or worst-case viewpoint of uncertainty which is motivated by a desire to find sets of optimal policies that maintain feasibility under a variety of operating conditions. In this paper, we explore an optimistic, or best-case view of uncertainty and show that it can be a fruitful approach. We show that these techniques can be used to address a wide variety of problems. First, we apply our methods in the context of robust linear programming, providing a method for reducing conservatism in intuitive ways that encode economically realistic modeling assumptions. Second, we look at problems in machine learning and find that this approach is strongly connected to the existing literature. Specifically, we provide a new interpretation for popular sparsity inducing non-convex regularization schemes. Additionally, we show that successful approaches for dealing with outliers and noise can be interpreted as optimistic robust optimization problems. Although many of the problems resulting from our approach are non-convex, we find that DCA or DCA-like optimization approaches can be intuitive and efficient.
Tasks
Published	2017-11-20
URL	http://arxiv.org/abs/1711.07511v1
PDF	http://arxiv.org/pdf/1711.07511v1.pdf
PWC	https://paperswithcode.com/paper/optimistic-robust-optimization-with
Repo
Framework

A Deep Neural Network Approach To Parallel Sentence Extraction


Title	A Deep Neural Network Approach To Parallel Sentence Extraction
Authors	Francis Grégoire, Philippe Langlais
Abstract	Parallel sentence extraction is a task addressing the data sparsity problem found in multilingual natural language processing applications. We propose an end-to-end deep neural network approach to detect translational equivalence between sentences in two different languages. In contrast to previous approaches, which typically rely on multiples models and various word alignment features, by leveraging continuous vector representation of sentences we remove the need of any domain specific feature engineering. Using a siamese bidirectional recurrent neural networks, our results against a strong baseline based on a state-of-the-art parallel sentence extraction system show a significant improvement in both the quality of the extracted parallel sentences and the translation performance of statistical machine translation systems. We believe this study is the first one to investigate deep learning for the parallel sentence extraction task.
Tasks	Feature Engineering, Machine Translation, Word Alignment
Published	2017-09-28
URL	http://arxiv.org/abs/1709.09783v1
PDF	http://arxiv.org/pdf/1709.09783v1.pdf
PWC	https://paperswithcode.com/paper/a-deep-neural-network-approach-to-parallel
Repo
Framework

Arrhythmia Classification from the Abductive Interpretation of Short Single-Lead ECG Records


Title	Arrhythmia Classification from the Abductive Interpretation of Short Single-Lead ECG Records
Authors	Tomás Teijeiro, Constantino A. García, Daniel Castro, Paulo Félix
Abstract	In this work we propose a new method for the rhythm classification of short single-lead ECG records, using a set of high-level and clinically meaningful features provided by the abductive interpretation of the records. These features include morphological and rhythm-related features that are used to build two classifiers: one that evaluates the record globally, using aggregated values for each feature; and another one that evaluates the record as a sequence, using a Recurrent Neural Network fed with the individual features for each detected heartbeat. The two classifiers are finally combined using the stacking technique, providing an answer by means of four target classes: Normal sinus rhythm, Atrial fibrillation, Other anomaly, and Noisy. The approach has been validated against the 2017 Physionet/CinC Challenge dataset, obtaining a final score of 0.83 and ranking first in the competition.
Tasks
Published	2017-11-10
URL	http://arxiv.org/abs/1711.03892v1
PDF	http://arxiv.org/pdf/1711.03892v1.pdf
PWC	https://paperswithcode.com/paper/arrhythmia-classification-from-the-abductive
Repo
Framework

Pictures of Combinatorial Cubes


Title	Pictures of Combinatorial Cubes
Authors	André Wagner
Abstract	We prove that the 8-point algorithm always fails to reconstruct a unique fundamental matrix $F$ independent on the camera positions, when its input are image point configurations that are perspective projections of the vertices of a combinatorial cube in $\mathbb{R}^3$. We give an algorithm that improves the 7- and 8-point algorithm in such a pathological situation. Additionally we analyze the regions of focal point positions where a reconstruction of $F$ is possible at all, when the world points are the vertices of a combinatorial cube in $\mathbb{R}^3$.
Tasks
Published	2017-07-20
URL	http://arxiv.org/abs/1707.06563v1
PDF	http://arxiv.org/pdf/1707.06563v1.pdf
PWC	https://paperswithcode.com/paper/pictures-of-combinatorial-cubes
Repo
Framework

Prepaid or Postpaid? That is the question. Novel Methods of Subscription Type Prediction in Mobile Phone Services


Title	Prepaid or Postpaid? That is the question. Novel Methods of Subscription Type Prediction in Mobile Phone Services
Authors	Yongjun Liao, Wei Du, Márton Karsai, Carlos Sarraute, Martin Minnoni, Eric Fleury
Abstract	In this paper we investigate the behavioural differences between mobile phone customers with prepaid and postpaid subscriptions. Our study reveals that (a) postpaid customers are more active in terms of service usage and (b) there are strong structural correlations in the mobile phone call network as connections between customers of the same subscription type are much more frequent than those between customers of different subscription types. Based on these observations we provide methods to detect the subscription type of customers by using information about their personal call statistics, and also their egocentric networks simultaneously. The key of our first approach is to cast this classification problem as a problem of graph labelling, which can be solved by max-flow min-cut algorithms. Our experiments show that, by using both user attributes and relationships, the proposed graph labelling approach is able to achieve a classification accuracy of $\sim 87%$, which outperforms by $\sim 7%$ supervised learning methods using only user attributes. In our second problem we aim to infer the subscription type of customers of external operators. We propose via approximate methods to solve this problem by using node attributes, and a two-ways indirect inference method based on observed homophilic structural correlations. Our results have straightforward applications in behavioural prediction and personal marketing.
Tasks
Published	2017-06-30
URL	http://arxiv.org/abs/1706.10172v1
PDF	http://arxiv.org/pdf/1706.10172v1.pdf
PWC	https://paperswithcode.com/paper/prepaid-or-postpaid-that-is-the-question
Repo
Framework

Telepath: Understanding Users from a Human Vision Perspective in Large-Scale Recommender Systems


Title	Telepath: Understanding Users from a Human Vision Perspective in Large-Scale Recommender Systems
Authors	Yu Wang, Jixing Xu, Aohan Wu, Mantian Li, Yang He, Jinghe Hu, Weipeng P. Yan
Abstract	Designing an e-commerce recommender system that serves hundreds of millions of active users is a daunting challenge. From a human vision perspective, there’re two key factors that affect users’ behaviors: items’ attractiveness and their matching degree with users’ interests. This paper proposes Telepath, a vision-based bionic recommender system model, which understands users from such perspective. Telepath is a combination of a convolutional neural network (CNN), a recurrent neural network (RNN) and deep neural networks (DNNs). Its CNN subnetwork simulates the human vision system to extract key visual signals of items’ attractiveness and generate corresponding activations. Its RNN and DNN subnetworks simulate cerebral cortex to understand users’ interest based on the activations generated from browsed items. In practice, the Telepath model has been launched to JD’s recommender system and advertising system. For one of the major item recommendation blocks on the JD app, click-through rate (CTR), gross merchandise value (GMV) and orders have increased 1.59%, 8.16% and 8.71% respectively. For several major ads publishers of JD demand-side platform, CTR, GMV and return on investment have increased 6.58%, 61.72% and 65.57% respectively by the first launch, and further increased 2.95%, 41.75% and 41.37% respectively by the second launch.
Tasks	Recommendation Systems
Published	2017-09-01
URL	http://arxiv.org/abs/1709.00300v2
PDF	http://arxiv.org/pdf/1709.00300v2.pdf
PWC	https://paperswithcode.com/paper/telepath-understanding-users-from-a-human
Repo
Framework

Adversarial Example Defenses: Ensembles of Weak Defenses are not Strong


Title	Adversarial Example Defenses: Ensembles of Weak Defenses are not Strong
Authors	Warren He, James Wei, Xinyun Chen, Nicholas Carlini, Dawn Song
Abstract	Ongoing research has proposed several methods to defend neural networks against adversarial examples, many of which researchers have shown to be ineffective. We ask whether a strong defense can be created by combining multiple (possibly weak) defenses. To answer this question, we study three defenses that follow this approach. Two of these are recently proposed defenses that intentionally combine components designed to work well together. A third defense combines three independent defenses. For all the components of these defenses and the combined defenses themselves, we show that an adaptive adversary can create adversarial examples successfully with low distortion. Thus, our work implies that ensemble of weak defenses is not sufficient to provide strong defense against adversarial examples.
Tasks
Published	2017-06-15
URL	http://arxiv.org/abs/1706.04701v1
PDF	http://arxiv.org/pdf/1706.04701v1.pdf
PWC	https://paperswithcode.com/paper/adversarial-example-defenses-ensembles-of
Repo
Framework

Deep Affordance-grounded Sensorimotor Object Recognition


Title	Deep Affordance-grounded Sensorimotor Object Recognition
Authors	Spyridon Thermos, Georgios Th. Papadopoulos, Petros Daras, Gerasimos Potamianos
Abstract	It is well-established by cognitive neuroscience that human perception of objects constitutes a complex process, where object appearance information is combined with evidence about the so-called object “affordances”, namely the types of actions that humans typically perform when interacting with them. This fact has recently motivated the “sensorimotor” approach to the challenging task of automatic object recognition, where both information sources are fused to improve robustness. In this work, the aforementioned paradigm is adopted, surpassing current limitations of sensorimotor object recognition research. Specifically, the deep learning paradigm is introduced to the problem for the first time, developing a number of novel neuro-biologically and neuro-physiologically inspired architectures that utilize state-of-the-art neural networks for fusing the available information sources in multiple ways. The proposed methods are evaluated using a large RGB-D corpus, which is specifically collected for the task of sensorimotor object recognition and is made publicly available. Experimental results demonstrate the utility of affordance information to object recognition, achieving an up to 29% relative error reduction by its inclusion.
Tasks	Object Recognition
Published	2017-04-10
URL	http://arxiv.org/abs/1704.02787v1
PDF	http://arxiv.org/pdf/1704.02787v1.pdf
PWC	https://paperswithcode.com/paper/deep-affordance-grounded-sensorimotor-object
Repo
Framework

Statistical Analysis of Dice CAPTCHA Usability


Title	Statistical Analysis of Dice CAPTCHA Usability
Authors	Darko Brodić, Alessia Amelio, Ivo R. Draganov
Abstract	In this paper the elements of the CAPTCHA usability are analyzed. CAPTCHA, as a time progressive element in computer science, has been under constant interest of ordinary, professional as well as the scientific users of the Internet. The analysis is given based on the usability elements of CAPTCHA which are abbreviated as user-centric approach to the CAPTCHA. To demonstrate it, the specific type of Dice CAPTCHA is used in the experiment. The experiment is conducted on 190 Internet users with different demographic characteristics on laptop and tablet computers. The obtained results are statistically processed. At the end, the results are compared and conclusion of their use is drawn.
Tasks
Published	2017-06-30
URL	http://arxiv.org/abs/1706.10177v1
PDF	http://arxiv.org/pdf/1706.10177v1.pdf
PWC	https://paperswithcode.com/paper/statistical-analysis-of-dice-captcha
Repo
Framework

Entity Linking for Queries by Searching Wikipedia Sentences


Title	Entity Linking for Queries by Searching Wikipedia Sentences
Authors	Chuanqi Tan, Furu Wei, Pengjie Ren, Weifeng Lv, Ming Zhou
Abstract	We present a simple yet effective approach for linking entities in queries. The key idea is to search sentences similar to a query from Wikipedia articles and directly use the human-annotated entities in the similar sentences as candidate entities for the query. Then, we employ a rich set of features, such as link-probability, context-matching, word embeddings, and relatedness among candidate entities as well as their related entities, to rank the candidates under a regression based framework. The advantages of our approach lie in two aspects, which contribute to the ranking process and final linking result. First, it can greatly reduce the number of candidate entities by filtering out irrelevant entities with the words in the query. Second, we can obtain the query sensitive prior probability in addition to the static link-probability derived from all Wikipedia articles. We conduct experiments on two benchmark datasets on entity linking for queries, namely the ERD14 dataset and the GERDAQ dataset. Experimental results show that our method outperforms state-of-the-art systems and yields 75.0% in F1 on the ERD14 dataset and 56.9% on the GERDAQ dataset.
Tasks	Entity Linking, Word Embeddings
Published	2017-04-10
URL	http://arxiv.org/abs/1704.02788v3
PDF	http://arxiv.org/pdf/1704.02788v3.pdf
PWC	https://paperswithcode.com/paper/entity-linking-for-queries-by-searching
Repo
Framework