January 27, 2020

2948 words 14 mins read

Paper Group ANR 1264

Approximate matrix completion based on cavity method. Improving CCTA based lesions’ hemodynamic significance assessment by accounting for partial volume modeling in automatic coronary lumen segmentation. Parallelism Theorem and Derived Rules for Parallel Coherent Transformations. Efficient GAN-based method for cyber-intrusion detection. Using dynam …

Approximate matrix completion based on cavity method


Title	Approximate matrix completion based on cavity method
Authors	Chihiro Noguchi, Yoshiyuki Kabashima
Abstract	In order to solve large matrix completion problems with practical computational cost, an approximate approach based on matrix factorization has been widely used. Alternating least squares (ALS) and stochastic gradient descent (SGD) are two major algorithms to this end. In this study, we propose a new algorithm, namely cavity-based matrix factorization (CBMF) and approximate cavity-based matrix factorization (ACBMF), which are developed based on the cavity method from statistical mechanics. ALS yields solutions with less iterations when compared to those of SGD. This is because its update rules are described in a closed form although it entails higher computational cost. CBMF can also write its update rules in a closed form, and its computational cost is lower than that of ALS. ACBMF is proposed to compensate a disadvantage of CBMF in terms of relatively high memory cost. We experimentally illustrate that the proposed methods outperform the two existing algorithms in terms of convergence speed per iteration, and it can work under the condition where observed entries are relatively fewer. Additionally, in contrast to SGD, (A)CBMF does not require scheduling of the learning rate.
Tasks	Matrix Completion
Published	2019-06-29
URL	https://arxiv.org/abs/1907.00138v1
PDF	https://arxiv.org/pdf/1907.00138v1.pdf
PWC	https://paperswithcode.com/paper/approximate-matrix-completion-based-on-cavity
Repo
Framework

Improving CCTA based lesions’ hemodynamic significance assessment by accounting for partial volume modeling in automatic coronary lumen segmentation


Title	Improving CCTA based lesions’ hemodynamic significance assessment by accounting for partial volume modeling in automatic coronary lumen segmentation
Authors	Moti Freiman, Hannes Nickisch, Sven Prevrhal, Holger Schmitt, Mani Vembar, Pál Maurovich-Horvat, Patrick Donnelly, Liran Goshen
Abstract	Purpose: The goal of this study was to assess the potential added benefit of accounting for partial volume effects (PVE) in an automatic coronary lumen segmentation algorithm from coronary computed tomography angiography (CCTA). Materials and methods: We assessed the potential added value of PVE integration as a part of the automatic coronary lumen segmentation algorithm by means of segmentation accuracy using the MICCAI 2012 challenge framework and by means of flow simulation overall accuracy, sensitivity, specificity, negative and positive predictive values and the receiver operated characteristic (ROC) area under the curve. We also evaluated the potential benefit of accounting for PVE in automatic segmentation for flow-simulation for lesions that were diagnosed as obstructive based on CCTA, which could have indicated a need for an invasive exam and revascularization. Results: Our segmentation algorithm improves the maximal surface distance error by ~39% compared to previously published method on the 18 datasets 50 from the MICCAI 2012 challenge with comparable Dice and mean surface distance. Results with and without accounting for PVE were comparable. In contrast, integrating PVE analysis into an automatic coronary lumen segmentation algorithm improved the flow simulation specificity from 0.6 to 0.68 with the same sensitivity of 0.83. Also, accounting for PVE improved the area under the ROC curve for detecting hemodynamically significant CAD from 0.76 to 0.8 compared to automatic segmentation without PVE analysis with invasive FFR threshold of 0.8 as the reference standard. The improvement in the AUC was statistically significant (N=76, Delong’s test, p=0.012). Conclusion: Accounting for the partial volume effects in automatic coronary lumen segmentation algorithms has the potential to improve the accuracy of CCTA-based hemodynamic assessment of coronary artery lesions.
Tasks
Published	2019-06-24
URL	https://arxiv.org/abs/1906.09763v1
PDF	https://arxiv.org/pdf/1906.09763v1.pdf
PWC	https://paperswithcode.com/paper/improving-ccta-based-lesions-hemodynamic
Repo
Framework

Parallelism Theorem and Derived Rules for Parallel Coherent Transformations


Title	Parallelism Theorem and Derived Rules for Parallel Coherent Transformations
Authors	Thierry Boy de la Tour
Abstract	An Independent Parallelism Theorem is proven in the theory of adhesive HLR categories. It shows the bijective correspondence between sequential independent and parallel independent direct derivations in the Weak Double-Pushout framework, see [2]. The parallel derivations are expressed by means of Parallel Coherent Transformations (PCTs), hence without assuming the existence of coproducts compatible with M as in the standard Parallelism Theorem. It is aslo shown that a derived rule can be extracted from any PCT, in the sense that to any direct derivation of this rule corresponds a valid PCT.
Tasks
Published	2019-07-08
URL	https://arxiv.org/abs/1907.06585v1
PDF	https://arxiv.org/pdf/1907.06585v1.pdf
PWC	https://paperswithcode.com/paper/parallelism-theorem-and-derived-rules-for
Repo
Framework

Efficient GAN-based method for cyber-intrusion detection


Title	Efficient GAN-based method for cyber-intrusion detection
Authors	Hongyu Chen, Li Jiang
Abstract	Ubiquitous anomalies endanger the security of our system constantly. They may bring irreversible damages to the system and cause leakage of privacy. Thus, it is of vital importance to promptly detect these anomalies. Traditional supervised methods such as Decision Trees and Support Vector Machine (SVM) are used to classify normality and abnormality. However, in some case the abnormal status are largely rarer than normal status, which leads to decision bias of these methods. Generative adversarial network (GAN) has been proposed to handle the case. With its strong generative ability, it only needs to learn the distribution of normal status, and identify the abnormal status through the gap between it and the learned distribution. Nevertheless, existing GAN-based models are not suitable to process data with discrete values, leading to immense degradation of detection performance. To cope with the discrete features, in this paper, we propose an efficient GAN-based model with specifically-designed loss function. Experiment results show that our model outperforms state-of-the-art models on discrete dataset and remarkably reduce the overhead.
Tasks	Anomaly Detection, Intrusion Detection
Published	2019-04-04
URL	https://arxiv.org/abs/1904.02426v2
PDF	https://arxiv.org/pdf/1904.02426v2.pdf
PWC	https://paperswithcode.com/paper/gan-based-method-for-cyber-intrusion
Repo
Framework

Using dynamic routing to extract intermediate features for developing scalable capsule networks


Title	Using dynamic routing to extract intermediate features for developing scalable capsule networks
Authors	Bodhisatwa Mandal, Swarnendu Ghosh, Ritesh Sarkhel, Nibaran Das, Mita Nasipuri
Abstract	Capsule networks have gained a lot of popularity in short time due to its unique approach to model equivariant class specific properties as capsules from images. However the dynamic routing algorithm comes with a steep computational complexity. In the proposed approach we aim to create scalable versions of the capsule networks that are much faster and provide better accuracy in problems with higher number of classes. By using dynamic routing to extract intermediate features instead of generating output class specific capsules, a large increase in the computational speed has been observed. Moreover, by extracting equivariant feature capsules instead of class specific capsules, the generalization capability of the network has also increased as a result of which there is a boost in accuracy.
Tasks
Published	2019-07-13
URL	https://arxiv.org/abs/1907.06062v1
PDF	https://arxiv.org/pdf/1907.06062v1.pdf
PWC	https://paperswithcode.com/paper/using-dynamic-routing-to-extract-intermediate
Repo
Framework

Endoscopy artifact detection (EAD 2019) challenge dataset


Title	Endoscopy artifact detection (EAD 2019) challenge dataset
Authors	Sharib Ali, Felix Zhou, Christian Daul, Barbara Braden, Adam Bailey, Stefano Realdon, James East, Georges Wagnières, Victor Loschenov, Enrico Grisan, Walter Blondel, Jens Rittscher
Abstract	Endoscopic artifacts are a core challenge in facilitating the diagnosis and treatment of diseases in hollow organs. Precise detection of specific artifacts like pixel saturations, motion blur, specular reflections, bubbles and debris is essential for high-quality frame restoration and is crucial for realizing reliable computer-assisted tools for improved patient care. At present most videos in endoscopy are currently not analyzed due to the abundant presence of multi-class artifacts in video frames. Through the endoscopic artifact detection (EAD 2019) challenge, we address this key bottleneck problem by solving the accurate identification and localization of endoscopic frame artifacts to enable further key quantitative analysis of unusable video frames such as mosaicking and 3D reconstruction which is crucial for delivering improved patient care. This paper summarizes the challenge tasks and describes the dataset and evaluation criteria established in the EAD 2019 challenge.
Tasks	3D Reconstruction
Published	2019-05-08
URL	https://arxiv.org/abs/1905.03209v1
PDF	https://arxiv.org/pdf/1905.03209v1.pdf
PWC	https://paperswithcode.com/paper/endoscopy-artifact-detection-ead-2019
Repo
Framework

Incorporating Interlocutor-Aware Context into Response Generation on Multi-Party Chatbots


Title	Incorporating Interlocutor-Aware Context into Response Generation on Multi-Party Chatbots
Authors	Cao Liu, Kang Liu, Shizhu He, Zaiqing Nie, Jun Zhao
Abstract	Conventional chatbots focus on two-party response generation, which simplifies the real dialogue scene. In this paper, we strive toward a novel task of Response Generation on Multi-Party Chatbot (RGMPC), where the generated responses heavily rely on the interlocutors’ roles (e.g., speaker and addressee) and their utterances. Unfortunately, complex interactions among the interlocutors’ roles make it challenging to precisely capture conversational contexts and interlocutors’ information. Facing this challenge, we present a response generation model which incorporates Interlocutor-aware Contexts into Recurrent Encoder-Decoder frameworks (ICRED) for RGMPC. Specifically, we employ interactive representations to capture dialogue contexts for different interlocutors. Moreover, we leverage an addressee memory to enhance contextual interlocutor information for the target addressee. Finally, we construct a corpus for RGMPC based on an existing open-access dataset. Automatic and manual evaluations demonstrate that the ICRED remarkably outperforms strong baselines.
Tasks	Chatbot
Published	2019-10-29
URL	https://arxiv.org/abs/1910.13106v1
PDF	https://arxiv.org/pdf/1910.13106v1.pdf
PWC	https://paperswithcode.com/paper/incorporating-interlocutor-aware-context-into
Repo
Framework

PL-NMF: Parallel Locality-Optimized Non-negative Matrix Factorization


Title	PL-NMF: Parallel Locality-Optimized Non-negative Matrix Factorization
Authors	Gordon E. Moon, Aravind Sukumaran-Rajam, Srinivasan Parthasarathy, P. Sadayappan
Abstract	Non-negative Matrix Factorization (NMF) is a key kernel for unsupervised dimension reduction used in a wide range of applications, including topic modeling, recommender systems and bioinformatics. Due to the compute-intensive nature of applications that must perform repeated NMF, several parallel implementations have been developed in the past. However, existing parallel NMF algorithms have not addressed data locality optimizations, which are critical for high performance since data movement costs greatly exceed the cost of arithmetic/logic operations on current computer systems. In this paper, we devise a parallel NMF algorithm based on the HALS (Hierarchical Alternating Least Squares) scheme that incorporates algorithmic transformations to enhance data locality. Efficient realizations of the algorithm on multi-core CPUs and GPUs are developed, demonstrating significant performance improvement over existing state-of-the-art parallel NMF algorithms.
Tasks	Dimensionality Reduction, Recommendation Systems
Published	2019-04-16
URL	http://arxiv.org/abs/1904.07935v1
PDF	http://arxiv.org/pdf/1904.07935v1.pdf
PWC	https://paperswithcode.com/paper/pl-nmf-parallel-locality-optimized-non
Repo
Framework

Cluster, Classify, Regress: A General Method For Learning Discountinous Functions


Title	Cluster, Classify, Regress: A General Method For Learning Discountinous Functions
Authors	David E. Bernholdt, Mark R. Cianciosa, Clement Etienam, David L. Green, Kody J. H. Law, J. M. Park
Abstract	This paper presents a method for solving the supervised learning problem in which the output is highly nonlinear and discontinuous. It is proposed to solve this problem in three stages: (i) cluster the pairs of input-output data points, resulting in a label for each point; (ii) classify the data, where the corresponding label is the output; and finally (iii) perform one separate regression for each class, where the training data corresponds to the subset of the original input-output pairs which have that label according to the classifier. It has not yet been proposed to combine these 3 fundamental building blocks of machine learning in this simple and powerful fashion. This can be viewed as a form of deep learning, where any of the intermediate layers can itself be deep. The utility and robustness of the methodology is illustrated on some toy problems, including one example problem arising from simulation of plasma fusion in a tokamak.
Tasks
Published	2019-05-15
URL	https://arxiv.org/abs/1905.06220v2
PDF	https://arxiv.org/pdf/1905.06220v2.pdf
PWC	https://paperswithcode.com/paper/cluster-classify-regress-a-general-method-for
Repo
Framework

An Unsupervised Deep Learning Method for Parallel Cardiac MRI via Time-Interleaved Sampling


Title	An Unsupervised Deep Learning Method for Parallel Cardiac MRI via Time-Interleaved Sampling
Authors	Yanjie Zhu, Ziwen Ke, Jing Cheng, Sen Jia, Yuanyuan Liu, Haifeng Wang, Leslie Ying, Xin Liu, Hairong Zheng, Dong Liang
Abstract	Deep learning has achieved good success in cardiac magnetic resonance imaging (MRI) reconstruction, in which convolutional neural networks (CNNs) learn the mapping from undersampled k-space to fully sampled images. Although these deep learning methods can improve reconstruction quality without complex parameter selection or a lengthy reconstruction time compared with iterative methods, the following issues still need to be addressed: 1) all of these methods are based on big data and require a large amount of fully sampled MRI data, which is always difficult for cardiac MRI; 2) All of these methods are only applicable for single-channel images without exploring coil correlation. In this paper, we propose an unsupervised deep learning method for parallel cardiac MRI via a time-interleaved sampling strategy. Specifically, a time-interleaved acquisition scheme is developed to build a set of fully encoded reference data by directly merging the k-space data of adjacent time frames. Then these fully encoded data can be used to train a parallel network for reconstructing images of each coil separately. Finally, the images from each coil are combined together via a CNN to implicitly explore the correlations between coils. The comparisons with classic k-t FOCUSS, k-t SLR and L+S methods on in vivo datasets show that our method can achieve improved reconstruction results in an extremely short amount of time.
Tasks
Published	2019-12-20
URL	https://arxiv.org/abs/1912.12177v1
PDF	https://arxiv.org/pdf/1912.12177v1.pdf
PWC	https://paperswithcode.com/paper/an-unsupervised-deep-learning-method-for
Repo
Framework

Spectral Perturbation Meets Incomplete Multi-view Data


Title	Spectral Perturbation Meets Incomplete Multi-view Data
Authors	Hao Wang, Linlin Zong, Bing Liu, Yan Yang, Wei Zhou
Abstract	Beyond existing multi-view clustering, this paper studies a more realistic clustering scenario, referred to as incomplete multi-view clustering, where a number of data instances are missing in certain views. To tackle this problem, we explore spectral perturbation theory. In this work, we show a strong link between perturbation risk bounds and incomplete multi-view clustering. That is, as the similarity matrix fed into spectral clustering is a quantity bounded in magnitude O(1), we transfer the missing problem from data to similarity and tailor a matrix completion method for incomplete similarity matrix. Moreover, we show that the minimization of perturbation risk bounds among different views maximizes the final fusion result across all views. This provides a solid fusion criteria for multi-view data. We motivate and propose a Perturbation-oriented Incomplete multi-view Clustering (PIC) method. Experimental results demonstrate the effectiveness of the proposed method.
Tasks	Matrix Completion
Published	2019-05-31
URL	https://arxiv.org/abs/1906.00098v1
PDF	https://arxiv.org/pdf/1906.00098v1.pdf
PWC	https://paperswithcode.com/paper/190600098
Repo
Framework

Winning the Big Data Technologies Horizon Prize: Fast and reliable forecasting of electricity grid traffic by identification of recurrent fluctuations


Title	Winning the Big Data Technologies Horizon Prize: Fast and reliable forecasting of electricity grid traffic by identification of recurrent fluctuations
Authors	Jose M. G. Vilar
Abstract	This paper provides a description of the approach and methodology I used in winning the European Union Big Data Technologies Horizon Prize on data-driven prediction of electricity grid traffic. The methodology relies on identifying typical short-term recurrent fluctuations, which is subsequently refined through a regression-of-fluctuations approach. The key points and strategic considerations that led to selecting or discarding different methodological aspects are also discussed. The criteria include adaptability to changing conditions, reliability with outliers and missing data, robustness to noise, and efficiency in implementation.
Tasks
Published	2019-02-12
URL	http://arxiv.org/abs/1902.04337v1
PDF	http://arxiv.org/pdf/1902.04337v1.pdf
PWC	https://paperswithcode.com/paper/winning-the-big-data-technologies-horizon
Repo
Framework

Learning vector representation of local content and matrix representation of local motion, with implications for V1


Title	Learning vector representation of local content and matrix representation of local motion, with implications for V1
Authors	Ruiqi Gao, Jianwen Xie, Siyuan Huang, Yufan Ren, Song-Chun Zhu, Ying Nian Wu
Abstract	This paper proposes a representational model for image pair such as consecutive video frames that are related by local pixel displacements, in the hope that the model may shed light on motion perception in primary visual cortex (V1). The model couples the following two components. (1) The vector representations of local contents of images. (2) The matrix representations of local pixel displacements caused by the relative motions between the agent and the objects in the 3D scene. When the image frame undergoes changes due to local pixel displacements, the vectors are multiplied by the matrices that represent the local displacements. Our experiments show that our model can learn to infer local motions. Moreover, the model can learn Gabor-like filter pairs of quadrature phases.
Tasks
Published	2019-01-24
URL	https://arxiv.org/abs/1902.03871v4
PDF	https://arxiv.org/pdf/1902.03871v4.pdf
PWC	https://paperswithcode.com/paper/learning-vector-representation-of-content-and
Repo
Framework

Multi-agent Learning for Neural Machine Translation


Title	Multi-agent Learning for Neural Machine Translation
Authors	Tianchi Bi, Hao Xiong, Zhongjun He, Hua Wu, Haifeng Wang
Abstract	Conventional Neural Machine Translation (NMT) models benefit from the training with an additional agent, e.g., dual learning, and bidirectional decoding with one agent decoding from left to right and the other decoding in the opposite direction. In this paper, we extend the training framework to the multi-agent scenario by introducing diverse agents in an interactive updating process. At training time, each agent learns advanced knowledge from others, and they work together to improve translation quality. Experimental results on NIST Chinese-English, IWSLT 2014 German-English, WMT 2014 English-German and large-scale Chinese-English translation tasks indicate that our approach achieves absolute improvements over the strong baseline systems and shows competitive performance on all tasks.
Tasks	Machine Translation
Published	2019-09-03
URL	https://arxiv.org/abs/1909.01101v1
PDF	https://arxiv.org/pdf/1909.01101v1.pdf
PWC	https://paperswithcode.com/paper/multi-agent-learning-for-neural-machine
Repo
Framework

Evaluating Style Transfer for Text


Title	Evaluating Style Transfer for Text
Authors	Remi Mir, Bjarke Felbo, Nick Obradovich, Iyad Rahwan
Abstract	Research in the area of style transfer for text is currently bottlenecked by a lack of standard evaluation practices. This paper aims to alleviate this issue by experimentally identifying best practices with a Yelp sentiment dataset. We specify three aspects of interest (style transfer intensity, content preservation, and naturalness) and show how to obtain more reliable measures of them from human evaluation than in previous work. We propose a set of metrics for automated evaluation and demonstrate that they are more strongly correlated and in agreement with human judgment: direction-corrected Earth Mover’s Distance, Word Mover’s Distance on style-masked texts, and adversarial classification for the respective aspects. We also show that the three examined models exhibit tradeoffs between aspects of interest, demonstrating the importance of evaluating style transfer models at specific points of their tradeoff plots. We release software with our evaluation metrics to facilitate research.
Tasks	Style Transfer
Published	2019-04-04
URL	http://arxiv.org/abs/1904.02295v1
PDF	http://arxiv.org/pdf/1904.02295v1.pdf
PWC	https://paperswithcode.com/paper/evaluating-style-transfer-for-text
Repo
Framework