January 30, 2020

3306 words 16 mins read

Paper Group ANR 435

Evaluating the Supervised and Zero-shot Performance of Multi-lingual Translation Models. Fuzzy Rough Set Feature Selection to Enhance Phishing Attack Detection. In defense of OSVOS. A Comprehensive Study of Alzheimer’s Disease Classification Using Convolutional Neural Networks. HTMLPhish: Enabling Phishing Web Page Detection by Applying Deep Learni …

Evaluating the Supervised and Zero-shot Performance of Multi-lingual Translation Models


Title	Evaluating the Supervised and Zero-shot Performance of Multi-lingual Translation Models
Authors	Chris Hokamp, John Glover, Demian Gholipour
Abstract	We study several methods for full or partial sharing of the decoder parameters of multilingual NMT models. We evaluate both fully supervised and zero-shot translation performance in 110 unique translation directions using only the WMT 2019 shared task parallel datasets for training. We use additional test sets and re-purpose evaluation methods recently used for unsupervised MT in order to evaluate zero-shot translation performance for language pairs where no gold-standard parallel data is available. To our knowledge, this is the largest evaluation of multi-lingual translation yet conducted in terms of the total size of the training data we use, and in terms of the diversity of zero-shot translation pairs we evaluate. We conduct an in-depth evaluation of the translation performance of different models, highlighting the trade-offs between methods of sharing decoder parameters. We find that models which have task-specific decoder parameters outperform models where decoder parameters are fully shared across all tasks.
Tasks
Published	2019-06-24
URL	https://arxiv.org/abs/1906.09675v1
PDF	https://arxiv.org/pdf/1906.09675v1.pdf
PWC	https://paperswithcode.com/paper/evaluating-the-supervised-and-zero-shot
Repo
Framework

Fuzzy Rough Set Feature Selection to Enhance Phishing Attack Detection


Title	Fuzzy Rough Set Feature Selection to Enhance Phishing Attack Detection
Authors	Mahdieh Zabihimayvan, Derek Doran
Abstract	Phishing as one of the most well-known cybercrime activities is a deception of online users to steal their personal or confidential information by impersonating a legitimate website. Several machine learning-based strategies have been proposed to detect phishing websites. These techniques are dependent on the features extracted from the website samples. However, few studies have actually considered efficient feature selection for detecting phishing attacks. In this work, we investigate an agreement on the definitive features which should be used in phishing detection. We apply Fuzzy Rough Set (FRS) theory as a tool to select most effective features from three benchmarked data sets. The selected features are fed into three often used classifiers for phishing detection. To evaluate the FRS feature selection in developing a generalizable phishing detection, the classifiers are trained by a separate out-of-sample data set of 14,000 website samples. The maximum F-measure gained by FRS feature selection is 95% using Random Forest classification. Also, there are 9 universal features selected by FRS over all the three data sets. The F-measure value using this universal feature set is approximately 93% which is a comparable result in contrast to the FRS performance. Since the universal feature set contains no features from third-part services, this finding implies that with no inquiry from external sources, we can gain a faster phishing detection which is also robust toward zero-day attacks.
Tasks	Feature Selection
Published	2019-03-13
URL	http://arxiv.org/abs/1903.05675v1
PDF	http://arxiv.org/pdf/1903.05675v1.pdf
PWC	https://paperswithcode.com/paper/fuzzy-rough-set-feature-selection-to-enhance
Repo
Framework

In defense of OSVOS


Title	In defense of OSVOS
Authors	Yu Liu, Yutong Dai, Anh-Dzung Doan, Lingqiao Liu, Ian Reid
Abstract	As a milestone for video object segmentation, one-shot video object segmentation (OSVOS) has achieved a large margin compared to the conventional optical-flow based methods regarding to the segmentation accuracy. Its excellent performance mainly benefit from the three-step training mechanism, that are: (1) acquiring object features on the base dataset (i.e. ImageNet), (2) training the parent network on the training set of the target dataset (i.e. DAVIS-2016) to be capable of differentiating the object of interest from the background. (3) online fine-tuning the interested object on the first frame of the target test set to overfit its appearance, then the model can be utilized to segment the same object in the rest frames of that video. In this paper, we argue that for the step (2), OSVOS has the limitation to ‘overemphasize’ the generic semantic object information while ‘dilute’ the instance cues of the object(s), which largely block the whole training process. Through adding a common module, video loss, which we formulate with various forms of constraints (including weighted BCE loss, high-dimensional triplet loss, as well as a novel mixed instance-aware video loss), to train the parent network in the step (2), the network is then better prepared for the step (3), i.e. online fine-tuning on the target instance. Through extensive experiments using different network structures as the backbone, we show that the proposed video loss module can improve the segmentation performance significantly, compared to that of OSVOS. Meanwhile, since video loss is a common module, it can be generalized to other fine-tuning based methods and similar vision tasks such as depth estimation and saliency detection.
Tasks	Depth Estimation, Optical Flow Estimation, Saliency Detection, Semantic Segmentation, Video Object Segmentation, Video Semantic Segmentation
Published	2019-08-19
URL	https://arxiv.org/abs/1908.06692v2
PDF	https://arxiv.org/pdf/1908.06692v2.pdf
PWC	https://paperswithcode.com/paper/in-defense-of-osvos
Repo
Framework

A Comprehensive Study of Alzheimer’s Disease Classification Using Convolutional Neural Networks


Title	A Comprehensive Study of Alzheimer’s Disease Classification Using Convolutional Neural Networks
Authors	Ziqiang Guan, Ritesh Kumar, Yi Ren Fung, Yeahuay Wu, Madalina Fiterau
Abstract	A plethora of deep learning models have been developed for the task of Alzheimer’s disease classification from brain MRI scans. Many of these models report high performance, achieving three-class classification accuracy of up to 95%. However, it is common for these studies to draw performance comparisons between models that are trained on different subsets of a dataset or use varying imaging preprocessing techniques, making it difficult to objectively assess model performance. Furthermore, many of these works do not provide details such as hyperparameters, the specific MRI scans used, or their source code, making it difficult to replicate their experiments. To address these concerns, we present a comprehensive study of some of the deep learning methods and architectures on the full set of images available from ADNI. We find that, (1) classification using 3D models gives an improvement of 1% in our setup, at the cost of significantly longer training time and more computation power, (2) with our dataset, pre-training yields minimal ($<0.5%$) improvement in model performance, (3) most popular convolutional neural network models yield similar performance when compared to each other. Lastly, we briefly compare the effects of two image preprocessing programs: FreeSurfer and Clinica, and find that the spatially normalized and segmented outputs from Clinica increased the accuracy of model prediction from 63% to 89% when compared to FreeSurfer images.
Tasks
Published	2019-04-16
URL	http://arxiv.org/abs/1904.07950v1
PDF	http://arxiv.org/pdf/1904.07950v1.pdf
PWC	https://paperswithcode.com/paper/a-comprehensive-study-of-alzheimers-disease
Repo
Framework

HTMLPhish: Enabling Phishing Web Page Detection by Applying Deep Learning Techniques on HTML Analysis


Title	HTMLPhish: Enabling Phishing Web Page Detection by Applying Deep Learning Techniques on HTML Analysis
Authors	Chidimma Opara, Bo Wei, Yingke Chen
Abstract	Recently, the development and implementation of phishing attacks require little technical skills and costs. This uprising has led to an ever-growing number of phishing attacks on the World Wide Web. Consequently, proactive techniques to fight phishing attacks have become extremely necessary. In this paper, we propose HTMLPhish, a deep learning based data-driven end-to-end automatic phishing web page classification approach. Specifically, HTMLPhish receives the content of the HTML document of a web page and employs Convolutional Neural Networks (CNNs) to learn the semantic dependencies in the textual contents of the HTML. The CNNs learn appropriate feature representations from the HTML document embeddings without extensive manual feature engineering. Furthermore, our proposed approach of the concatenation of the word and character embeddings allows our model to manage new features and ensure easy extrapolation to test data. We conduct extensive experiments on a dataset that provides a distribution of phishing to benign web pages obtainable in the real-world that yields an impressive True Positive Rate. Also, HTMLPhish is a completely language-independent and client-side strategy which can, therefore, conduct web page phishing detection regardless of the textual language.
Tasks	Feature Engineering
Published	2019-08-28
URL	https://arxiv.org/abs/1909.01135v2
PDF	https://arxiv.org/pdf/1909.01135v2.pdf
PWC	https://paperswithcode.com/paper/htmlphish-enabling-accurate-phishing-web-page
Repo
Framework

A Dynamic Analysis of Energy Storage with Renewable and Diesel Generation using Volterra Equations


Title	A Dynamic Analysis of Energy Storage with Renewable and Diesel Generation using Volterra Equations
Authors	Denis Sidorov, Ildar Muftahov, Nikita Tomin, Dmitriy Karamov, Daniil Panasetsky, Aliona Dreglea, Fang Liu, Aoife Foley
Abstract	Energy storage systems will play a key role in the power system of the twenty first century considering the large penetrations of variable renewable energy, growth in transport electrification and decentralisation of heating loads. Therefore reliable real time methods to optimise energy storage, demand response and generation are vital for power system operations. This paper presents a concise review of battery energy storage and an example of battery modelling for renewable energy applications and second details an adaptive approach to solve this load levelling problem with storage. A dynamic evolutionary model based on the first kind Volterra integral equation is used in both cases. A direct regularised numerical method is employed to find the least-cost dispatch of the battery in terms of integral equation solution. Validation on real data shows that the proposed evolutionary Volterra model effectively generalises conventional discrete integral model taking into account both state of health and the availability of generation/storage.
Tasks
Published	2019-08-04
URL	https://arxiv.org/abs/1908.01310v1
PDF	https://arxiv.org/pdf/1908.01310v1.pdf
PWC	https://paperswithcode.com/paper/a-dynamic-analysis-of-energy-storage-with
Repo
Framework

Radically Compositional Cognitive Concepts


Title	Radically Compositional Cognitive Concepts
Authors	Toby B. St Clere Smithe
Abstract	Despite ample evidence that our concepts, our cognitive architecture, and mathematics itself are all deeply compositional, few models take advantage of this structure. We therefore propose a radically compositional approach to computational neuroscience, drawing on the methods of applied category theory. We describe how these tools grant us a means to overcome complexity and improve interpretability, and supply a rigorous common language for scientific modelling, analogous to the type theories of computer science. As a case study, we sketch how to translate from compositional narrative concepts to neural circuits and back again.
Tasks
Published	2019-11-14
URL	https://arxiv.org/abs/1911.06602v1
PDF	https://arxiv.org/pdf/1911.06602v1.pdf
PWC	https://paperswithcode.com/paper/radically-compositional-cognitive-concepts
Repo
Framework

Machine learning driven synthesis of few-layered WTe2


Title	Machine learning driven synthesis of few-layered WTe2
Authors	Manzhang Xu, Bijun Tang, Chao Zhu, Yuhao Lu, Chao Zhu, Lu Zheng, Jingyu Zhang, Nannan Han, Yuxi Guo, Jun Di, Pin Song, Yongmin He, Lixing Kang, Zhiyong Zhang, Wu Zhao, Cuntai Guan, Xuewen Wang, Zheng Liu
Abstract	Reducing the lateral scale of two-dimensional (2D) materials to one-dimensional (1D) has attracted substantial research interest not only to achieve competitive electronic device applications but also for the exploration of fundamental physical properties. Controllable synthesis of high-quality 1D nanoribbons (NRs) is thus highly desirable and essential for the further study. Traditional exploration of the optimal synthesis conditions of novel materials is based on the trial-and-error approach, which is time consuming, costly and laborious. Recently, machine learning (ML) has demonstrated promising capability in guiding material synthesis through effectively learning from the past data and then making recommendations. Here, we report the implementation of supervised ML for the chemical vapor deposition (CVD) synthesis of high-quality 1D few-layered WTe2 nanoribbons (NRs). The synthesis parameters of the WTe2 NRs are optimized by the trained ML model. On top of that, the growth mechanism of as-synthesized 1T’ few-layered WTe2 NRs is further proposed, which may inspire the growth strategies for other 1D nanostructures. Our findings suggest that ML is a powerful and efficient approach to aid the synthesis of 1D nanostructures, opening up new opportunities for intelligent material development.
Tasks
Published	2019-10-10
URL	https://arxiv.org/abs/1910.04603v1
PDF	https://arxiv.org/pdf/1910.04603v1.pdf
PWC	https://paperswithcode.com/paper/machine-learning-driven-synthesis-of-few
Repo
Framework

Multimodal Deep Learning for Mental Disorders Prediction from Audio Speech Samples


Title	Multimodal Deep Learning for Mental Disorders Prediction from Audio Speech Samples
Authors	Habibeh Naderi, Behrouz Haji Soleimani, Stan Matwin
Abstract	Key features of mental illnesses are reflected in speech. Our research focuses on designing a multimodal deep learning structure that automatically extracts salient features from recorded speech samples for predicting various mental disorders including depression, bipolar, and schizophrenia. We adopt a variety of pre-trained models to extract embeddings from both audio and text segments. We use several state-of-the-art embedding techniques including BERT, FastText, and Doc2VecC for the text representation learning and WaveNet and VGG-ish models for audio encoding. We also leverage huge auxiliary emotion-labeled text and audio corpora to train emotion-specific embeddings and use transfer learning in order to address the problem of insufficient annotated multimodal data available. All these embeddings are then combined into a joint representation in a multimodal fusion layer and finally a recurrent neural network is used to predict the mental disorder. Our results show that mental disorders can be predicted with acceptable accuracy through multimodal analysis of clinical interviews.
Tasks	Representation Learning, Transfer Learning
Published	2019-09-03
URL	https://arxiv.org/abs/1909.01067v4
PDF	https://arxiv.org/pdf/1909.01067v4.pdf
PWC	https://paperswithcode.com/paper/multimodal-deep-learning-for-mental-disorders
Repo
Framework

Efficient Cross-Validation for Semi-Supervised Learning


Title	Efficient Cross-Validation for Semi-Supervised Learning
Authors	Yong Liu, Jian Li, Guangjun Wu, Lizhong Ding, Weiping Wang
Abstract	Manifold regularization, such as laplacian regularized least squares (LapRLS) and laplacian support vector machine (LapSVM), has been widely used in semi-supervised learning, and its performance greatly depends on the choice of some hyper-parameters. Cross-validation (CV) is the most popular approach for selecting the optimal hyper-parameters, but it has high complexity due to multiple times of learner training. In this paper, we provide a method to approximate the CV for manifold regularization based on a notion of robust statistics, called Bouligand influence function (BIF). We first provide a strategy for approximating the CV via the Taylor expansion of BIF. Then, we show how to calculate the BIF for general loss function,and further give the approximate CV criteria for model selection in manifold regularization. The proposed approximate CV for manifold regularization requires training only once, hence can significantly improve the efficiency of traditional CV. Experimental results show that our approximate CV has no statistical discrepancy with the original one, but much smaller time cost.
Tasks	Model Selection
Published	2019-02-13
URL	http://arxiv.org/abs/1902.04768v1
PDF	http://arxiv.org/pdf/1902.04768v1.pdf
PWC	https://paperswithcode.com/paper/efficient-cross-validation-for-semi
Repo
Framework

LEARNet Dynamic Imaging Network for Micro Expression Recognition


Title	LEARNet Dynamic Imaging Network for Micro Expression Recognition
Authors	Monu Verma, Santosh Kumar Vipparthi, Girdhari Singh, Subrahmanyam Murala
Abstract	Unlike prevalent facial expressions, micro expressions have subtle, involuntary muscle movements which are short-lived in nature. These minute muscle movements reflect true emotions of a person. Due to the short duration and low intensity, these micro-expressions are very difficult to perceive and interpret correctly. In this paper, we propose the dynamic representation of micro-expressions to preserve facial movement information of a video in a single frame. We also propose a Lateral Accretive Hybrid Network (LEARNet) to capture micro-level features of an expression in the facial region. The LEARNet refines the salient expression features in accretive manner by incorporating accretion layers (AL) in the network. The response of the AL holds the hybrid feature maps generated by prior laterally connected convolution layers. Moreover, LEARNet architecture incorporates the cross decoupled relationship between convolution layers which helps in preserving the tiny but influential facial muscle change information. The visual responses of the proposed LEARNet depict the effectiveness of the system by preserving both high- and micro-level edge features of facial expression. The effectiveness of the proposed LEARNet is evaluated on four benchmark datasets: CASME-I, CASME-II, CAS(ME)^2 and SMIC. The experimental results after investigation show a significant improvement of 4.03%, 1.90%, 1.79% and 2.82% as compared with ResNet on CASME-I, CASME-II, CAS(ME)^2 and SMIC datasets respectively.
Tasks
Published	2019-04-20
URL	http://arxiv.org/abs/1904.09410v1
PDF	http://arxiv.org/pdf/1904.09410v1.pdf
PWC	https://paperswithcode.com/paper/190409410
Repo
Framework

Meta Filter Pruning to Accelerate Deep Convolutional Neural Networks


Title	Meta Filter Pruning to Accelerate Deep Convolutional Neural Networks
Authors	Yang He, Ping Liu, Linchao Zhu, Yi Yang
Abstract	Existing methods usually utilize pre-defined criterions, such as p-norm, to prune unimportant filters. There are two major limitations in these methods. First, the relations of the filters are largely ignored. The filters usually work jointly to make an accurate prediction in a collaborative way. Similar filters will have equivalent effects on the network prediction, and the redundant filters can be further pruned. Second, the pruning criterion remains unchanged during training. As the network updated at each iteration, the filter distribution also changes continuously. The pruning criterions should also be adaptively switched. In this paper, we propose Meta Filter Pruning (MFP) to solve the above problems. First, as a complement to the existing p-norm criterion, we introduce a new pruning criterion considering the filter relation via filter distance. Additionally, we build a meta pruning framework for filter pruning, so that our method could adaptively select the most appropriate pruning criterion as the filter distribution changes. Experiments validate our approach on two image classification benchmarks. Notably, on ILSVRC-2012, our MFP reduces more than 50% FLOPs on ResNet-50 with only 0.44% top-5 accuracy loss.
Tasks	Image Classification
Published	2019-04-08
URL	http://arxiv.org/abs/1904.03961v1
PDF	http://arxiv.org/pdf/1904.03961v1.pdf
PWC	https://paperswithcode.com/paper/meta-filter-pruning-to-accelerate-deep
Repo
Framework

Improving Distantly-supervised Entity Typing with Compact Latent Space Clustering


Title	Improving Distantly-supervised Entity Typing with Compact Latent Space Clustering
Authors	Bo Chen, Xiaotao Gu, Yufeng Hu, Siliang Tang, Guoping Hu, Yueting Zhuang, Xiang Ren
Abstract	Recently, distant supervision has gained great success on Fine-grained Entity Typing (FET). Despite its efficiency in reducing manual labeling efforts, it also brings the challenge of dealing with false entity type labels, as distant supervision assigns labels in a context agnostic manner. Existing works alleviated this issue with partial-label loss, but usually suffer from confirmation bias, which means the classifier fit a pseudo data distribution given by itself. In this work, we propose to regularize distantly supervised models with Compact Latent Space Clustering (CLSC) to bypass this problem and effectively utilize noisy data yet. Our proposed method first dynamically constructs a similarity graph of different entity mentions; infer the labels of noisy instances via label propagation. Based on the inferred labels, mention embeddings are updated accordingly to encourage entity mentions with close semantics to form a compact cluster in the embedding space,thus leading to better classification performance. Extensive experiments on standard benchmarks show that our CLSC model consistently outperforms state-of-the-art distantly supervised entity typing systems by a significant margin.
Tasks	Entity Typing
Published	2019-04-13
URL	http://arxiv.org/abs/1904.06475v1
PDF	http://arxiv.org/pdf/1904.06475v1.pdf
PWC	https://paperswithcode.com/paper/improving-distantly-supervised-entity-typing
Repo
Framework

A tractable ellipsoidal approximation for voltage regulation problems


Title	A tractable ellipsoidal approximation for voltage regulation problems
Authors	Pan Li, Baihong Jin, Ruoxuan Xiong, Dai Wang, Alberto Sangiovanni-Vincentelli, Baosen Zhang
Abstract	We present a machine learning approach to the solution of chance constrained optimizations in the context of voltage regulation problems in power system operation. The novelty of our approach resides in approximating the feasible region of uncertainty with an ellipsoid. We formulate this problem using a learning model similar to Support Vector Machines (SVM) and propose a sampling algorithm that efficiently trains the model. We demonstrate our approach on a voltage regulation problem using standard IEEE distribution test feeders.
Tasks
Published	2019-03-09
URL	http://arxiv.org/abs/1903.03763v1
PDF	http://arxiv.org/pdf/1903.03763v1.pdf
PWC	https://paperswithcode.com/paper/a-tractable-ellipsoidal-approximation-for
Repo
Framework

Learning to Detect Collisions for Continuum Manipulators without a Prior Model


Title	Learning to Detect Collisions for Continuum Manipulators without a Prior Model
Authors	Shahriar Sefati, Shahin Sefati, Iulian Iordachita, Russell H. Taylor, Mehran Armand
Abstract	Due to their flexibility, dexterity, and compact size, Continuum Manipulators (CMs) can enhance minimally invasive interventions. In these procedures, the CM may be operated in proximity of sensitive organs; therefore, requiring accurate and appropriate feedback when colliding with their surroundings. Conventional CM collision detection algorithms rely on a combination of exact CM constrained kinematics model, geometrical assumptions such as constant curvature behavior, a priori knowledge of the environmental constraint geometry, and/or additional sensors to scan the environment or sense contacts. In this paper, we propose a data-driven machine learning approach using only the available sensory information, without requiring any prior geometrical assumptions, model of the CM or the surrounding environment. The proposed algorithm is implemented and evaluated on a non-constant curvature CM, equipped with Fiber Bragg Grating (FBG) optical sensors for shape sensing purposes. Results demonstrate successful detection of collisions in constrained environments with soft and hard obstacles with unknown stiffness and location.
Tasks
Published	2019-08-12
URL	https://arxiv.org/abs/1908.04354v1
PDF	https://arxiv.org/pdf/1908.04354v1.pdf
PWC	https://paperswithcode.com/paper/learning-to-detect-collisions-for-continuum
Repo
Framework