January 30, 2020

3226 words 16 mins read

Paper Group ANR 279

An Automated Spectral Clustering for Multi-scale Data. PhonSenticNet: A Cognitive Approach to Microtext Normalization for Concept-Level Sentiment Analysis. Group Average Treatment Effects for Observational Studies. A Note On The Popularity of Stochastic Optimization Algorithms in Different Fields: A Quantitative Analysis from 2007 to 2017. Deep Lea …

An Automated Spectral Clustering for Multi-scale Data


Title	An Automated Spectral Clustering for Multi-scale Data
Authors	Milad Afzalan, Farrokh Jazizadeh
Abstract	Spectral clustering algorithms typically require a priori selection of input parameters such as the number of clusters, a scaling parameter for the affinity measure, or ranges of these values for parameter tuning. Despite efforts for automating the process of spectral clustering, the task of grouping data in multi-scale and higher dimensional spaces is yet to be explored. This study presents a spectral clustering heuristic algorithm that obviates the need for an input by estimating the parameters from the data itself. Specifically, it introduces the heuristic of iterative eigengap search with (1) global scaling and (2) local scaling. These approaches estimate the scaling parameter and implement iterative eigengap quantification along a search tree to reveal dissimilarities at different scales of a feature space and identify clusters. The performance of these approaches has been tested on various real-world datasets of power variation with multi-scale nature and gene expression. Our findings show that iterative eigengap search with a PCA-based global scaling scheme can discover different patterns with an accuracy of higher than 90% in most cases without asking for a priori input information.
Tasks
Published	2019-02-06
URL	http://arxiv.org/abs/1902.01990v1
PDF	http://arxiv.org/pdf/1902.01990v1.pdf
PWC	https://paperswithcode.com/paper/an-automated-spectral-clustering-for-multi
Repo
Framework

PhonSenticNet: A Cognitive Approach to Microtext Normalization for Concept-Level Sentiment Analysis


Title	PhonSenticNet: A Cognitive Approach to Microtext Normalization for Concept-Level Sentiment Analysis
Authors	Ranjan Satapathy, Aalind Singh, Erik Cambria
Abstract	With the current upsurge in the usage of social media platforms, the trend of using short text (microtext) in place of standard words has seen a significant rise. The usage of microtext poses a considerable performance issue in concept-level sentiment analysis, since models are trained on standard words. This paper discusses the impact of coupling sub-symbolic (phonetics) with symbolic (machine learning) Artificial Intelligence to transform the out-of-vocabulary concepts into their standard in-vocabulary form. The phonetic distance is calculated using the Sorensen similarity algorithm. The phonetically similar invocabulary concepts thus obtained are then used to compute the correct polarity value, which was previously being miscalculated because of the presence of microtext. Our proposed framework increases the accuracy of polarity detection by 6% as compared to the earlier model. This also validates the fact that microtext normalization is a necessary pre-requisite for the sentiment analysis task.
Tasks	Sentiment Analysis
Published	2019-04-24
URL	http://arxiv.org/abs/1905.01967v1
PDF	http://arxiv.org/pdf/1905.01967v1.pdf
PWC	https://paperswithcode.com/paper/190501967
Repo
Framework

Group Average Treatment Effects for Observational Studies


Title	Group Average Treatment Effects for Observational Studies
Authors	Daniel Jacob
Abstract	The paper proposes an estimator to make inference of heterogeneous treatment effects sorted by impact groups (GATES) for non-randomised experiments. The groups can be understood as a broader aggregation of the conditional average treatment effect (CATE) where the number of groups is set in advance. In economics, this approach is similar to pre-analysis plans. Observational studies are standard in policy evaluation from labour markets, educational surveys and other empirical studies. To control for a potential selection-bias, we implement a doubly-robust estimator in the first stage. We use machine learning methods to learn the conditional mean functions as well as the propensity score. The group average treatment effect is then estimated via a linear projection model. The linear model is easy to interpret, provides p-values and confidence intervals, and limits the danger of finding spurious heterogeneity due to small subgroups in the CATE. To control for confounding in the linear model, we use Neyman-orthogonal moments to partial out the effect that covariates have on both, the treatment assignment and the outcome. The result is a best linear predictor for effect heterogeneity based on impact groups. We find that our proposed method has lower absolute errors as well as smaller bias than the benchmark doubly-robust estimator. We further introduce a bagging type averaging for the CATE function for each observation to avoid biases through sample splitting. The advantage of the proposed method is a robust linear estimation of heterogeneous group treatment effects in observational studies.
Tasks
Published	2019-11-07
URL	https://arxiv.org/abs/1911.02688v5
PDF	https://arxiv.org/pdf/1911.02688v5.pdf
PWC	https://paperswithcode.com/paper/group-average-treatment-effects-for
Repo
Framework

A Note On The Popularity of Stochastic Optimization Algorithms in Different Fields: A Quantitative Analysis from 2007 to 2017


Title	A Note On The Popularity of Stochastic Optimization Algorithms in Different Fields: A Quantitative Analysis from 2007 to 2017
Authors	Son Duy Dao
Abstract	Stochastic optimization algorithms are often used to solve complex large-scale optimization problems in various fields. To date, there have been a number of stochastic optimization algorithms such as Genetic Algorithm, Cuckoo Search, Tabu Search, Simulated Annealing, Particle Swarm Optimization, Ant Colony Optimization, etc. Each algorithm has some advantages and disadvantages. Currently, there is no study that can help researchers to choose the most popular optimization algorithm to deal with the problems in different research fields. In this note, a quantitative analysis of the popularity of 14 stochastic optimization algorithms in 18 different research fields in the last ten years from 2007 to 2017 is provided. This quantitative analysis can help researchers/practitioners select the best optimization algorithm to solve complex large-scale optimization problems in the fields of Engineering, Computer science, Operations research, Mathematics, Physics, Chemistry, Automation control systems, Materials science, Energy fuels, Mechanics, Telecommunications, Thermodynamics, Optics, Environmental sciences ecology, Water resources, Transportation, Construction building technology, and Robotics.
Tasks	Stochastic Optimization
Published	2019-06-30
URL	https://arxiv.org/abs/1907.01453v2
PDF	https://arxiv.org/pdf/1907.01453v2.pdf
PWC	https://paperswithcode.com/paper/a-note-on-the-popularity-of-stochastic
Repo
Framework

Deep Learning at the Edge


Title	Deep Learning at the Edge
Authors	Sahar Voghoei, Navid Hashemi Tonekaboni, Jason G. Wallace, Hamid R. Arabnia
Abstract	The ever-increasing number of Internet of Things (IoT) devices has created a new computing paradigm, called edge computing, where most of the computations are performed at the edge devices, rather than on centralized servers. An edge device is an electronic device that provides connections to service providers and other edge devices; typically, such devices have limited resources. Since edge devices are resource-constrained, the task of launching algorithms, methods, and applications onto edge devices is considered to be a significant challenge. In this paper, we discuss one of the most widely used machine learning methods, namely, Deep Learning (DL) and offer a short survey on the recent approaches used to map DL onto the edge computing paradigm. We also provide relevant discussions about selected applications that would greatly benefit from DL at the edge.
Tasks
Published	2019-10-22
URL	https://arxiv.org/abs/1910.10231v1
PDF	https://arxiv.org/pdf/1910.10231v1.pdf
PWC	https://paperswithcode.com/paper/deep-learning-at-the-edge
Repo
Framework

Warm Up Cold-start Advertisements: Improving CTR Predictions via Learning to Learn ID Embeddings


Title	Warm Up Cold-start Advertisements: Improving CTR Predictions via Learning to Learn ID Embeddings
Authors	Feiyang Pan, Shuokai Li, Xiang Ao, Pingzhong Tang, Qing He
Abstract	Click-through rate (CTR) prediction has been one of the most central problems in computational advertising. Lately, embedding techniques that produce low-dimensional representations of ad IDs drastically improve CTR prediction accuracies. However, such learning techniques are data demanding and work poorly on new ads with little logging data, which is known as the cold-start problem. In this paper, we aim to improve CTR predictions during both the cold-start phase and the warm-up phase when a new ad is added to the candidate pool. We propose Meta-Embedding, a meta-learning-based approach that learns to generate desirable initial embeddings for new ad IDs. The proposed method trains an embedding generator for new ad IDs by making use of previously learned ads through gradient-based meta-learning. In other words, our method learns how to learn better embeddings. When a new ad comes, the trained generator initializes the embedding of its ID by feeding its contents and attributes. Next, the generated embedding can speed up the model fitting during the warm-up phase when a few labeled examples are available, compared to the existing initialization methods. Experimental results on three real-world datasets showed that Meta-Embedding can significantly improve both the cold-start and warm-up performances for six existing CTR prediction models, ranging from lightweight models such as Factorization Machines to complicated deep models such as PNN and DeepFM. All of the above apply to conversion rate (CVR) predictions as well.
Tasks	Click-Through Rate Prediction, Meta-Learning
Published	2019-04-25
URL	http://arxiv.org/abs/1904.11547v1
PDF	http://arxiv.org/pdf/1904.11547v1.pdf
PWC	https://paperswithcode.com/paper/warm-up-cold-start-advertisements-improving
Repo
Framework

Minimum Class Confusion for Versatile Domain Adaptation


Title	Minimum Class Confusion for Versatile Domain Adaptation
Authors	Ying Jin, Ximei Wang, Mingsheng Long, Jianmin Wang
Abstract	There are a variety of DA scenarios subject to label sets and domain configurations, including closed-set and partial-set DA, as well as multi-source and multi-target DA. It is notable that existing DA methods are generally designed only for a specific scenario, and may underperform for scenarios they are not tailored to. A versatile method, which can handle several different scenarios without any extra modifications, is still remained to be explored. Towards such purpose, a more general inductive bias other than the domain alignment should be explored. In this paper, we delve into a missing piece of existing methods: class confusion, the tendency that a classifier confuses the predictions between the correct and ambiguous classes for target examples, which exists in all of the scenarios above. We unveil that reducing such pair-wise class confusion brings about significant transfer gains. Based on this, we propose a general loss function: Minimum Class Confusion (MCC). It can be characterized by (1) a non-adversarial DA method without explicitly deploying domain alignment, enjoying fast convergence speed (about 3 times faster than mainstream adversarial methods); (2) a versatile approach that can handle the four existing scenarios: Closed-Set, Partial-Set, Multi-Source, and Multi-Target DA, outperforming the state-of-the-art methods in these scenarios, especially on the largest and hardest dataset to date (7.25% on DomainNet). Strong performance in the two scenarios proposed in this paper: Multi-Source Partial and Multi-Target Partial DA, further proves its versatility. In addition, it can also be used as a general regularizer that is orthogonal and complementary to a variety of existing DA methods, accelerating convergence and pushing those readily competitive methods to a stronger level.
Tasks	Domain Adaptation
Published	2019-12-08
URL	https://arxiv.org/abs/1912.03699v2
PDF	https://arxiv.org/pdf/1912.03699v2.pdf
PWC	https://paperswithcode.com/paper/less-confusion-more-transferable-minimum
Repo
Framework

Synthetic Image Augmentation for Improved Classification using Generative Adversarial Networks


Title	Synthetic Image Augmentation for Improved Classification using Generative Adversarial Networks
Authors	Keval Doshi
Abstract	Object detection and recognition has been an ongoing research topic for a long time in the field of computer vision. Even in robotics, detecting the state of an object by a robot still remains a challenging task. Also, collecting data for each possible state is also not feasible. In this literature, we use a deep convolutional neural network with SVM as a classifier to help with recognizing the state of a cooking object. We also study how a generative adversarial network can be used for synthetic data augmentation and improving the classification accuracy. The main motivation behind this work is to estimate how well a robot could recognize the current state of an object
Tasks	Data Augmentation, Image Augmentation, Object Detection
Published	2019-07-31
URL	https://arxiv.org/abs/1907.13576v1
PDF	https://arxiv.org/pdf/1907.13576v1.pdf
PWC	https://paperswithcode.com/paper/synthetic-image-augmentation-for-improved
Repo
Framework

Parameter Tuning for Self-optimizing Software at Scale


Title	Parameter Tuning for Self-optimizing Software at Scale
Authors	Dmytro Pukhkaiev, Uwe Aßmann
Abstract	Efficiency of self-optimizing systems is heavily dependent on their optimization strategies, e.g., choosing exact or approximate solver. A choice of such a strategy, in turn, is influenced by numerous factors, such as re-optimization time, size of the problem, optimality constraints, etc. Exact solvers are domain-independent and can guarantee optimality but suffer from scaling, while approximate solvers offer a “good-enough” solution in exchange for a lack of generality and parameter-dependence. In this paper we discuss the trade-offs between exact and approximate optimizers for solving a quality-based software selection and hardware mapping problem from the scalability perspective. We show that even a simple heuristic can compete with thoroughly developed exact solvers under condition of an effective parameter tuning. Moreover, we discuss robustness of the obtained algorithm’s configuration. Last but not least, we present a software product line for parameter tuning, which comprise the main features of this process and can serve as a platform for further research in the area of parameter tuning.
Tasks
Published	2019-09-09
URL	https://arxiv.org/abs/1909.03814v1
PDF	https://arxiv.org/pdf/1909.03814v1.pdf
PWC	https://paperswithcode.com/paper/parameter-tuning-for-self-optimizing-software
Repo
Framework

A Hybrid Approach Towards Two Stage Bengali Question Classification Utilizing Smart Data Balancing Technique


Title	A Hybrid Approach Towards Two Stage Bengali Question Classification Utilizing Smart Data Balancing Technique
Authors	Md. Hasibur Rahman, Chowdhury Rafeed Rahman, Ruhul Amin, Md. Habibur Rahman Sifat, Afra Anika
Abstract	Question classification (QC) is the primary step of the Question Answering (QA) system. Question Classification (QC) system classifies the questions in particular classes so that Question Answering (QA) System can provide correct answers for the questions. Our system categorizes the factoid type questions asked in natural language after extracting features of the questions. We present a two stage QC system for Bengali. It utilizes one dimensional convolutional neural network for classifying questions into coarse classes in the first stage. Word2vec representation of existing words of the question corpus have been constructed and used for assisting 1D CNN. A smart data balancing technique has been employed for giving data hungry convolutional neural network the advantage of a greater number of effective samples to learn from. For each coarse class, a separate Stochastic Gradient Descent (SGD) based classifier has been used in order to differentiate among the finer classes within that coarse class. TF-IDF representation of each word has been used as feature for the SGD classifiers implemented as part of second stage classification. Experiments show the effectiveness of our proposed method for Bengali question classification.
Tasks	Question Answering
Published	2019-11-30
URL	https://arxiv.org/abs/1912.00127v3
PDF	https://arxiv.org/pdf/1912.00127v3.pdf
PWC	https://paperswithcode.com/paper/a-hybrid-approach-towards-two-stage-bengali
Repo
Framework

Learning to Approximate Directional Fields Defined over 2D Planes


Title	Learning to Approximate Directional Fields Defined over 2D Planes
Authors	Maria Taktasheva, Albert Matveev, Alexey Artemov, Evgeny Burnaev
Abstract	Reconstruction of directional fields is a need in many geometry processing tasks, such as image tracing, extraction of 3D geometric features, and finding principal surface directions. A common approach to the construction of directional fields from data relies on complex optimization procedures, which are usually poorly formalizable, require a considerable computational effort, and do not transfer across applications. In this work, we propose a deep learning-based approach and study the expressive power and generalization ability.
Tasks
Published	2019-07-01
URL	https://arxiv.org/abs/1907.00559v1
PDF	https://arxiv.org/pdf/1907.00559v1.pdf
PWC	https://paperswithcode.com/paper/learning-to-approximate-directional-fields
Repo
Framework

Robust exploration in linear quadratic reinforcement learning


Title	Robust exploration in linear quadratic reinforcement learning
Authors	Jack Umenberger, Mina Ferizbegovic, Thomas B. Schön, Håkan Hjalmarsson
Abstract	This paper concerns the problem of learning control policies for an unknown linear dynamical system to minimize a quadratic cost function. We present a method, based on convex optimization, that accomplishes this task robustly: i.e., we minimize the worst-case cost, accounting for system uncertainty given the observed data. The method balances exploitation and exploration, exciting the system in such a way so as to reduce uncertainty in the model parameters to which the worst-case cost is most sensitive. Numerical simulations and application to a hardware-in-the-loop servo-mechanism demonstrate the approach, with appreciable performance and robustness gains over alternative methods observed in both.
Tasks
Published	2019-06-04
URL	https://arxiv.org/abs/1906.01584v1
PDF	https://arxiv.org/pdf/1906.01584v1.pdf
PWC	https://paperswithcode.com/paper/robust-exploration-in-linear-quadratic
Repo
Framework

CartoonRenderer: An Instance-based Multi-Style Cartoon Image Translator


Title	CartoonRenderer: An Instance-based Multi-Style Cartoon Image Translator
Authors	Yugang Chen, Muchun Chen, Chaoyue Song, Bingbing Ni
Abstract	Instance based photo cartoonization is one of the challenging image stylization tasks which aim at transforming realistic photos into cartoon style images while preserving the semantic contents of the photos. State-of-the-art Deep Neural Networks (DNNs) methods still fail to produce satisfactory results with input photos in the wild, especially for photos which have high contrast and full of rich textures. This is due to that: cartoon style images tend to have smooth color regions and emphasized edges which are contradict to realistic photos which require clear semantic contents, i.e., textures, shapes etc. Previous methods have difficulty in satisfying cartoon style textures and preserving semantic contents at the same time. In this work, we propose a novel “CartoonRenderer” framework which utilizing a single trained model to generate multiple cartoon styles. In a nutshell, our method maps photo into a feature model and renders the feature model back into image space. In particular, cartoonization is achieved by conducting some transformation manipulation in the feature space with our proposed Soft-AdaIN. Extensive experimental results show our method produces higher quality cartoon style images than prior arts, with accurate semantic content preservation. In addition, due to the decoupling of whole generating process into “Modeling-Coordinating-Rendering” parts, our method could easily process higher resolution photos, which is intractable for existing methods.
Tasks	Image Stylization
Published	2019-11-14
URL	https://arxiv.org/abs/1911.06102v1
PDF	https://arxiv.org/pdf/1911.06102v1.pdf
PWC	https://paperswithcode.com/paper/cartoonrenderer-an-instance-based-multi-style
Repo
Framework

A Two-stage Classification Method for High-dimensional Data and Point Clouds


Title	A Two-stage Classification Method for High-dimensional Data and Point Clouds
Authors	Xiaohao Cai, Raymond Chan, Xiaoyu Xie, Tieyong Zeng
Abstract	High-dimensional data classification is a fundamental task in machine learning and imaging science. In this paper, we propose a two-stage multiphase semi-supervised classification method for classifying high-dimensional data and unstructured point clouds. To begin with, a fuzzy classification method such as the standard support vector machine is used to generate a warm initialization. We then apply a two-stage approach named SaT (smoothing and thresholding) to improve the classification. In the first stage, an unconstraint convex variational model is implemented to purify and smooth the initialization, followed by the second stage which is to project the smoothed partition obtained at stage one to a binary partition. These two stages can be repeated, with the latest result as a new initialization, to keep improving the classification quality. We show that the convex model of the smoothing stage has a unique solution and can be solved by a specifically designed primal-dual algorithm whose convergence is guaranteed. We test our method and compare it with the state-of-the-art methods on several benchmark data sets. The experimental results demonstrate clearly that our method is superior in both the classification accuracy and computation speed for high-dimensional data and point clouds.
Tasks
Published	2019-05-21
URL	https://arxiv.org/abs/1905.08538v1
PDF	https://arxiv.org/pdf/1905.08538v1.pdf
PWC	https://paperswithcode.com/paper/a-two-stage-classification-method-for-high
Repo
Framework

A Time Attention based Fraud Transaction Detection Framework


Title	A Time Attention based Fraud Transaction Detection Framework
Authors	Longfei Li, Ziqi Liu, Chaochao Chen, Ya-Lin Zhang, Jun Zhou, Xiaolong Li
Abstract	With online payment platforms being ubiquitous and important, fraud transaction detection has become the key for such platforms, to ensure user account safety and platform security. In this work, we present a novel method for detecting fraud transactions by leveraging patterns from both users’ static profiles and users’ dynamic behaviors in a unified framework. To address and explore the information of users’ behaviors in continuous time spaces, we propose to use \emph{time attention based recurrent layers} to embed the detailed information of the time interval, such as the durations of specific actions, time differences between different actions and sequential behavior patterns,etc., in the same latent space. We further combine the learned embeddings and users’ static profiles altogether in a unified framework. Extensive experiments validate the effectiveness of our proposed methods over state-of-the-art methods on various evaluation metrics, especially on \emph{recall at top percent} which is an important metric for measuring the balance between service experiences and risk of potential losses.
Tasks
Published	2019-12-26
URL	https://arxiv.org/abs/1912.11760v2
PDF	https://arxiv.org/pdf/1912.11760v2.pdf
PWC	https://paperswithcode.com/paper/a-time-attention-based-fraud-transaction
Repo
Framework