January 26, 2020

3224 words 16 mins read

Paper Group ANR 1606

Classification Logit Two-sample Testing by Neural Networks. Predictive Situation Awareness for Ebola Virus Disease using a Collective Intelligence Multi-Model Integration Platform: Bayes Cloud. Matching Embeddings for Domain Adaptation. On the Compositionality Prediction of Noun Phrases using Poincaré Embeddings. Injecting Hierarchy with U-Net Tran …

Classification Logit Two-sample Testing by Neural Networks


Title	Classification Logit Two-sample Testing by Neural Networks
Authors	Xiuyuan Cheng, Alexander Cloninger
Abstract	The recent success of generative adversarial networks and variational learning suggests training a classifier network may work well in addressing the classical two-sample problem. Network-based tests have the computational advantage that the algorithm scales to large samples. This paper proposes to use the difference of the logit of a trained neural network classifier evaluated on the two finite samples as the test statistic. Theoretically, we prove the testing power to differentiate two smooth densities given that the network is sufficiently parametrized, by comparing the learned logit function to the log ratio of the densities, the latter maximizing the population training objective. When the two densities lie on or near to low-dimensional manifolds embedded in possibly high-dimensional space, the needed network complexity is reduced to only depending on the intrinsic manifold geometry. In experiments, the method demonstrates better performance than previous network-based tests which use the classification accuracy as the test statistic, and compares favorably to certain kernel maximum mean discrepancy (MMD) tests on synthetic and hand-written digits datasets.
Tasks
Published	2019-09-25
URL	https://arxiv.org/abs/1909.11298v1
PDF	https://arxiv.org/pdf/1909.11298v1.pdf
PWC	https://paperswithcode.com/paper/classification-logit-two-sample-testing-by
Repo
Framework

Predictive Situation Awareness for Ebola Virus Disease using a Collective Intelligence Multi-Model Integration Platform: Bayes Cloud


Title	Predictive Situation Awareness for Ebola Virus Disease using a Collective Intelligence Multi-Model Integration Platform: Bayes Cloud
Authors	Cheol Young Park, Shou Matsumoto, Jubyung Ha, YoungWon Park
Abstract	The humanity has been facing a plethora of challenges associated with infectious diseases, which kill more than 6 million people a year. Although continuous efforts have been applied to relieve the potential damages from such misfortunate events, it is unquestionable that there are many persisting challenges yet to overcome. One related issue we particularly address here is the assessment and prediction of such epidemics. In this field of study, traditional and ad-hoc models frequently fail to provide proper predictive situation awareness (PSAW), characterized by understanding the current situations and predicting the future situations. Comprehensive PSAW for infectious disease can support decision making and help to hinder disease spread. In this paper, we develop a computing system platform focusing on collective intelligence causal modeling, in order to support PSAW in the domain of infectious disease. Analyses of global epidemics require integration of multiple different data and models, which can be originated from multiple independent researchers. These models should be integrated to accurately assess and predict the infectious disease in terms of holistic view. The system shall provide three main functions: (1) collaborative causal modeling, (2) causal model integration, and (3) causal model reasoning. These functions are supported by subject-matter expert and artificial intelligence (AI), with uncertainty treatment. Subject-matter experts, as collective intelligence, develop causal models and integrate them as one joint causal model. The integrated causal model shall be used to reason about: (1) the past, regarding how the causal factors have occurred; (2) the present, regarding how the spread is going now; and (3) the future, regarding how it will proceed. Finally, we introduce one use case of predictive situation awareness for the Ebola virus disease.
Tasks	Decision Making
Published	2019-04-29
URL	https://arxiv.org/abs/1904.12958v2
PDF	https://arxiv.org/pdf/1904.12958v2.pdf
PWC	https://paperswithcode.com/paper/predictive-situation-awareness-for-ebola
Repo
Framework

Matching Embeddings for Domain Adaptation


Title	Matching Embeddings for Domain Adaptation
Authors	Manuel Pérez-Carrasco, Guillermo Cabrera-Vives, Pavlos Protopapas, Nicolás Astorga, Marouan Belhaj
Abstract	In this work we address the problem of transferring knowledge obtained from a vast annotated source domain to a low labeled or unlabeled target domain. We propose Adversarial Variational Domain Adaptation (AVDA), a semi-supervised domain adaptation method based on deep variational embedded representations. We use approximate inference and adversarial methods to map samples from source and target domains into an aligned semantic embedding. We show that on a semi-supervised few-shot scenario, our approach can be used to obtain a significant speed-up in performance when using an increasing number of labels on the target domain.
Tasks	Domain Adaptation
Published	2019-09-25
URL	https://arxiv.org/abs/1909.11651v3
PDF	https://arxiv.org/pdf/1909.11651v3.pdf
PWC	https://paperswithcode.com/paper/adversarial-variational-domain-adaptation
Repo
Framework

On the Compositionality Prediction of Noun Phrases using Poincaré Embeddings


Title	On the Compositionality Prediction of Noun Phrases using Poincaré Embeddings
Authors	Abhik Jana, Dmitry Puzyrev, Alexander Panchenko, Pawan Goyal, Chris Biemann, Animesh Mukherjee
Abstract	The compositionality degree of multiword expressions indicates to what extent the meaning of a phrase can be derived from the meaning of its constituents and their grammatical relations. Prediction of (non)-compositionality is a task that has been frequently addressed with distributional semantic models. We introduce a novel technique to blend hierarchical information with distributional information for predicting compositionality. In particular, we use hypernymy information of the multiword and its constituents encoded in the form of the recently introduced Poincar'e embeddings in addition to the distributional information to detect compositionality for noun phrases. Using a weighted average of the distributional similarity and a Poincar'e similarity function, we obtain consistent and substantial, statistically significant improvement across three gold standard datasets over state-of-the-art models based on distributional information only. Unlike traditional approaches that solely use an unsupervised setting, we have also framed the problem as a supervised task, obtaining comparable improvements. Further, we publicly release our Poincar'e embeddings, which are trained on the output of handcrafted lexical-syntactic patterns on a large corpus.
Tasks
Published	2019-06-07
URL	https://arxiv.org/abs/1906.03007v1
PDF	https://arxiv.org/pdf/1906.03007v1.pdf
PWC	https://paperswithcode.com/paper/on-the-compositionality-prediction-of-noun
Repo
Framework

Injecting Hierarchy with U-Net Transformers


Title	Injecting Hierarchy with U-Net Transformers
Authors	David Donahue, Vladislav Lialin, Anna Rumshisky
Abstract	The Transformer architecture has become increasingly popular over the past couple of years, owing to its impressive performance on a number of natural language processing (NLP) tasks. However, it may be argued that the Transformer architecture lacks an explicit hierarchical representation, as all computations occur on word-level representations alone, and therefore, learning structure poses a challenge for Transformer models. In the present work, we introduce hierarchical processing into the Transformer model, taking inspiration from the U-Net architecture, popular in computer vision for its hierarchical view of natural images. We propose a novel architecture that combines ideas from Transformer and U-Net models to incorporate hierarchy at multiple levels of abstraction. We empirically demonstrate that the proposed architecture outperforms the vanilla Transformer and strong baselines in the chit-chat dialogue and machine translation domains.
Tasks	Machine Translation
Published	2019-10-16
URL	https://arxiv.org/abs/1910.10488v1
PDF	https://arxiv.org/pdf/1910.10488v1.pdf
PWC	https://paperswithcode.com/paper/injecting-hierarchy-with-u-net-transformers
Repo
Framework

Improving Robustness of time series classifier with Neural ODE guided gradient based data augmentation


Title	Improving Robustness of time series classifier with Neural ODE guided gradient based data augmentation
Authors	Anindya Sarkar, Anirudh Sunder Raj, Raghu Sesha Iyengar
Abstract	Exploring adversarial attack vectors and studying their effects on machine learning algorithms has been of interest to researchers. Deep neural networks working with time series data have received lesser interest compared to their image counterparts in this context. In a recent finding, it has been revealed that current state-of-the-art deep learning time series classifiers are vulnerable to adversarial attacks. In this paper, we introduce two local gradient based and one spectral density based time series data augmentation techniques. We show that a model trained with data obtained using our techniques obtains state-of-the-art classification accuracy on various time series benchmarks. In addition, it improves the robustness of the model against some of the most common corruption techniques,such as Fast Gradient Sign Method (FGSM) and Basic Iterative Method (BIM).
Tasks	Adversarial Attack, Data Augmentation, Time Series
Published	2019-10-15
URL	https://arxiv.org/abs/1910.06813v1
PDF	https://arxiv.org/pdf/1910.06813v1.pdf
PWC	https://paperswithcode.com/paper/improving-robustness-of-time-series
Repo
Framework

CBOW Is Not All You Need: Combining CBOW with the Compositional Matrix Space Model


Title	CBOW Is Not All You Need: Combining CBOW with the Compositional Matrix Space Model
Authors	Florian Mai, Lukas Galke, Ansgar Scherp
Abstract	Continuous Bag of Words (CBOW) is a powerful text embedding method. Due to its strong capabilities to encode word content, CBOW embeddings perform well on a wide range of downstream tasks while being efficient to compute. However, CBOW is not capable of capturing the word order. The reason is that the computation of CBOW’s word embeddings is commutative, i.e., embeddings of XYZ and ZYX are the same. In order to address this shortcoming, we propose a learning algorithm for the Continuous Matrix Space Model, which we call Continual Multiplication of Words (CMOW). Our algorithm is an adaptation of word2vec, so that it can be trained on large quantities of unlabeled text. We empirically show that CMOW better captures linguistic properties, but it is inferior to CBOW in memorizing word content. Motivated by these findings, we propose a hybrid model that combines the strengths of CBOW and CMOW. Our results show that the hybrid CBOW-CMOW-model retains CBOW’s strong ability to memorize word content while at the same time substantially improving its ability to encode other linguistic information by 8%. As a result, the hybrid also performs better on 8 out of 11 supervised downstream tasks with an average improvement of 1.2%.
Tasks	Word Embeddings
Published	2019-02-18
URL	http://arxiv.org/abs/1902.06423v1
PDF	http://arxiv.org/pdf/1902.06423v1.pdf
PWC	https://paperswithcode.com/paper/cbow-is-not-all-you-need-combining-cbow-with
Repo
Framework

A framework for fake review detection in online consumer electronics retailers


Title	A framework for fake review detection in online consumer electronics retailers
Authors	Rodrigo Barbado, Oscar Araque, Carlos A. Iglesias
Abstract	The impact of online reviews on businesses has grown significantly during last years, being crucial to determine business success in a wide array of sectors, ranging from restaurants, hotels to e-commerce. Unfortunately, some users use unethical means to improve their online reputation by writing fake reviews of their businesses or competitors. Previous research has addressed fake review detection in a number of domains, such as product or business reviews in restaurants and hotels. However, in spite of its economical interest, the domain of consumer electronics businesses has not yet been thoroughly studied. This article proposes a feature framework for detecting fake reviews that has been evaluated in the consumer electronics domain. The contributions are fourfold: (i) Construction of a dataset for classifying fake reviews in the consumer electronics domain in four different cities based on scraping techniques; (ii) definition of a feature framework for fake review detection; (iii) development of a fake review classification method based on the proposed framework and (iv) evaluation and analysis of the results for each of the cities under study. We have reached an 82% F-Score on the classification task and the Ada Boost classifier has been proven to be the best one by statistical means according to the Friedman test.
Tasks
Published	2019-03-29
URL	http://arxiv.org/abs/1903.12452v1
PDF	http://arxiv.org/pdf/1903.12452v1.pdf
PWC	https://paperswithcode.com/paper/a-framework-for-fake-review-detection-in
Repo
Framework

Learning Classifiers on Positive and Unlabeled Data with Policy Gradient


Title	Learning Classifiers on Positive and Unlabeled Data with Policy Gradient
Authors	Tianyu Li, Chien-Chih Wang, Yukun Ma, Patricia Ortal, Qifang Zhao, Bjorn Stenger, Yu Hirate
Abstract	Existing algorithms aiming to learn a binary classifier from positive (P) and unlabeled (U) data generally require estimating the class prior or label noises ahead of building a classification model. However, the estimation and classifier learning are normally conducted in a pipeline instead of being jointly optimized. In this paper, we propose to alternatively train the two steps using reinforcement learning. Our proposal adopts a policy network to adaptively make assumptions on the labels of unlabeled data, while a classifier is built upon the output of the policy network and provides rewards to learn a better strategy. The dynamic and interactive training between the policy maker and the classifier can exploit the unlabeled data in a more effective manner and yield a significant improvement on the classification performance. Furthermore, we present two different approaches to represent the actions sampled from the policy. The first approach considers continuous actions as soft labels, while the other uses discrete actions as hard assignment of labels for unlabeled examples.We validate the effectiveness of the proposed method on two benchmark datasets as well as one e-commerce dataset. The result shows the proposed method is able to consistently outperform state-of-the-art methods in various settings.
Tasks
Published	2019-10-15
URL	https://arxiv.org/abs/1910.06535v1
PDF	https://arxiv.org/pdf/1910.06535v1.pdf
PWC	https://paperswithcode.com/paper/learning-classifiers-on-positive-and
Repo
Framework

Does BLEU Score Work for Code Migration?


Title	Does BLEU Score Work for Code Migration?
Authors	Ngoc Tran, Hieu Tran, Son Nguyen, Hoan Nguyen, Tien N. Nguyen
Abstract	Statistical machine translation (SMT) is a fast-growing sub-field of computational linguistics. Until now, the most popular automatic metric to measure the quality of SMT is BiLingual Evaluation Understudy (BLEU) score. Lately, SMT along with the BLEU metric has been applied to a Software Engineering task named code migration. (In)Validating the use of BLEU score could advance the research and development of SMT-based code migration tools. Unfortunately, there is no study to approve or disapprove the use of BLEU score for source code. In this paper, we conducted an empirical study on BLEU score to (in)validate its suitability for the code migration task due to its inability to reflect the semantics of source code. In our work, we use human judgment as the ground truth to measure the semantic correctness of the migrated code. Our empirical study demonstrates that BLEU does not reflect translation quality due to its weak correlation with the semantic correctness of translated code. We provided counter-examples to show that BLEU is ineffective in comparing the translation quality between SMT-based models. Due to BLEU’s ineffectiveness for code migration task, we propose an alternative metric RUBY, which considers lexical, syntactical, and semantic representations of source code. We verified that RUBY achieves a higher correlation coefficient with the semantic correctness of migrated code, 0.775 in comparison with 0.583 of BLEU score. We also confirmed the effectiveness of RUBY in reflecting the changes in translation quality of SMT-based translation models. With its advantages, RUBY can be used to evaluate SMT-based code migration models.
Tasks	Machine Translation
Published	2019-06-12
URL	https://arxiv.org/abs/1906.04903v1
PDF	https://arxiv.org/pdf/1906.04903v1.pdf
PWC	https://paperswithcode.com/paper/does-bleu-score-work-for-code-migration
Repo
Framework

Research on Autonomous Maneuvering Decision of UCAV based on Approximate Dynamic Programming


Title	Research on Autonomous Maneuvering Decision of UCAV based on Approximate Dynamic Programming
Authors	Zhencai Hu, Peng Gao, Fei Wang
Abstract	Unmanned aircraft systems can perform some more dangerous and difficult missions than manned aircraft systems. In some highly complicated and changeable tasks, such as air combat, the maneuvering decision mechanism is required to sense the combat situation accurately and make the optimal strategy in real-time. This paper presents a formulation of a 3-D one-on-one air combat maneuvering problem and an approximate dynamic programming approach for computing an optimal policy on autonomous maneuvering decision making. The aircraft learns combat strategies in a Reinforcement Leaning method, while sensing the environment, taking available maneuvering actions and getting feedback reward signals. To solve the problem of dimensional explosion in the air combat, the proposed method is implemented through feature selection, trajectory sampling, function approximation and Bellman backup operation in the air combat simulation environment. This approximate dynamic programming approach provides a fast response to a rapidly changing tactical situation, learns in long-term planning, without any explicitly coded air combat rule base.
Tasks	Decision Making, Feature Selection
Published	2019-08-27
URL	https://arxiv.org/abs/1908.10010v2
PDF	https://arxiv.org/pdf/1908.10010v2.pdf
PWC	https://paperswithcode.com/paper/research-on-autonomous-maneuvering-decision
Repo
Framework

Detecting Parking Spaces in a Parcel using Satellite Images


Title	Detecting Parking Spaces in a Parcel using Satellite Images
Authors	Murugesan Vadivel, SelvaKumar Murugan, Suriyadeepan Ramamoorthy, Vaidheeswaran Archana, Malaikannan Sankarasubbu
Abstract	Remote Sensing Images from satellites have been used in various domains for detecting and understanding structures on the ground surface. In this work, satellite images were used for localizing parking spaces and vehicles in parking lots for a given parcel using an RCNN based Neural Network Architectures. Parcel shapefiles and raster images from USGS image archive were used for developing images for both training and testing. Feature Pyramid based Mask RCNN yields average class accuracy of 97.56% for both parking spaces and vehicles
Tasks
Published	2019-08-28
URL	https://arxiv.org/abs/1909.05624v2
PDF	https://arxiv.org/pdf/1909.05624v2.pdf
PWC	https://paperswithcode.com/paper/detecting-parking-spaces-in-a-parcel-using
Repo
Framework

Fall of Empires: Breaking Byzantine-tolerant SGD by Inner Product Manipulation


Title	Fall of Empires: Breaking Byzantine-tolerant SGD by Inner Product Manipulation
Authors	Cong Xie, Sanmi Koyejo, Indranil Gupta
Abstract	Recently, new defense techniques have been developed to tolerate Byzantine failures for distributed machine learning. The Byzantine model captures workers that behave arbitrarily, including malicious and compromised workers. In this paper, we break two prevailing Byzantine-tolerant techniques. Specifically we show robust aggregation methods for synchronous SGD – coordinate-wise median and Krum – can be broken using new attack strategies based on inner product manipulation. We prove our results theoretically, as well as show empirical validation.
Tasks
Published	2019-03-10
URL	http://arxiv.org/abs/1903.03936v1
PDF	http://arxiv.org/pdf/1903.03936v1.pdf
PWC	https://paperswithcode.com/paper/fall-of-empires-breaking-byzantine-tolerant
Repo
Framework

Teacher-Students Knowledge Distillation for Siamese Trackers


Title	Teacher-Students Knowledge Distillation for Siamese Trackers
Authors	Yuanpei Liu, Xingping Dong, Xiankai Lu, Fahad Shahbaz Khan, Jianbing Shen, Steven Hoi
Abstract	In recent years, Siamese network based trackers have significantly advanced the state-of-the-art in real-time tracking. However, state-of-the-art Siamese trackers suffer from high memory cost which restricts their applicability in mobile applications having strict constraints on memory budget. To address this issue, we propose a novel distilled Siamese tracking framework to learn small, fast yet accurate trackers (students), which capture critical knowledge from large Siamese trackers (teachers) by a teacher-students knowledge distillation model. This model is intuitively inspired by a one-teacher vs multi-students learning mechanism, which is the most usual teaching method in the school. In particular, it contains a single teacher-student distillation model and a student-student knowledge sharing mechanism. The first one is designed by a tracking-specific distillation strategy to transfer knowledge from the teacher to students. The later is utilized for mutual learning between students to enable an in-depth knowledge understanding. To the best of our knowledge, we are the first to investigate knowledge distillation for Siamese trackers and propose a distilled Siamese tracking framework. We demonstrate the generality and effectiveness of our framework by conducting a theoretical analysis and extensive empirical evaluations on several popular Siamese trackers. The results on five tracking benchmarks clearly show that the proposed distilled trackers achieve compression rates up to 18$\times$ and frame-rates of $265$ FPS with speedups of 3$\times$, while obtaining similar or even slightly improved tracking accuracy.
Tasks	Object Tracking
Published	2019-07-24
URL	https://arxiv.org/abs/1907.10586v2
PDF	https://arxiv.org/pdf/1907.10586v2.pdf
PWC	https://paperswithcode.com/paper/teacher-students-knowledge-distillation-for
Repo
Framework

The Longer the Better? The Interplay Between Review Length and Line of Argumentation in Online Consumer Reviews


Title	The Longer the Better? The Interplay Between Review Length and Line of Argumentation in Online Consumer Reviews
Authors	Bernhard Lutz, Nicolas Pröllochs, Dirk Neumann
Abstract	Review helpfulness serves as focal point in understanding customers’ purchase decision-making process on online retailer platforms. An overwhelming majority of previous works find longer reviews to be more helpful than short reviews. In this paper, we propose that longer reviews should not be assumed to be uniformly more helpful; instead, we argue that the effect depends on the line of argumentation in the review text. To test this idea, we use a large dataset of customer reviews from Amazon in combination with a state-of-the-art approach from natural language processing that allows us to study argumentation lines at sentence level. Our empirical analysis suggests that the frequency of argumentation changes moderates the effect of review length on helpfulness. Altogether, we disprove the prevailing narrative that longer reviews are uniformly perceived as more helpful. Our findings allow retailer platforms to improve their customer feedback systems and to feature more useful product reviews.
Tasks	Decision Making
Published	2019-09-10
URL	https://arxiv.org/abs/1909.05192v3
PDF	https://arxiv.org/pdf/1909.05192v3.pdf
PWC	https://paperswithcode.com/paper/the-longer-the-better-the-interplay-between
Repo
Framework