January 31, 2020

3268 words 16 mins read

Paper Group ANR 156

To Detect Irregular Trade Behaviors In Stock Market By Using Graph Based Ranking Methods. PINE: Universal Deep Embedding for Graph Nodes via Partial Permutation Invariant Set Functions. Knee Cartilage Segmentation Using Diffusion-Weighted MRI. Heterogeneous-Temporal Graph Convolutional Networks: Make the Community Detection Much Better. Learning in …

To Detect Irregular Trade Behaviors In Stock Market By Using Graph Based Ranking Methods


Title	To Detect Irregular Trade Behaviors In Stock Market By Using Graph Based Ranking Methods
Authors	Loc Tran, Linh Tran
Abstract	To detect the irregular trade behaviors in the stock market is the important problem in machine learning field. These irregular trade behaviors are obviously illegal. To detect these irregular trade behaviors in the stock market, data scientists normally employ the supervised learning techniques. In this paper, we employ the three graph Laplacian based semi-supervised ranking methods to solve the irregular trade behavior detection problem. Experimental results show that that the un-normalized and symmetric normalized graph Laplacian based semi-supervised ranking methods outperform the random walk Laplacian based semi-supervised ranking method.
Tasks
Published	2019-09-04
URL	https://arxiv.org/abs/1909.08964v1
PDF	https://arxiv.org/pdf/1909.08964v1.pdf
PWC	https://paperswithcode.com/paper/to-detect-irregular-trade-behaviors-in-stock
Repo
Framework

PINE: Universal Deep Embedding for Graph Nodes via Partial Permutation Invariant Set Functions


Title	PINE: Universal Deep Embedding for Graph Nodes via Partial Permutation Invariant Set Functions
Authors	Shupeng Gui, Xiangliang Zhang, Pan Zhong, Shuang Qiu, Mingrui Wu, Jieping Ye, Zhengdao Wang, Ji Liu
Abstract	Graph node embedding aims at learning a vector representation for all nodes given a graph. It is a central problem in many machine learning tasks (e.g., node classification, recommendation, community detection). The key problem in graph node embedding lies in how to define the dependence to neighbors. Existing approaches specify (either explicitly or implicitly) certain dependencies on neighbors, which may lead to loss of subtle but important structural information within the graph and other dependencies among neighbors. This intrigues us to ask the question: can we design a model to give the maximal flexibility of dependencies to each node’s neighborhood. In this paper, we propose a novel graph node embedding (named PINE) via a novel notion of partial permutation invariant set function, to capture any possible dependence. Our method 1) can learn an arbitrary form of the representation function from the neighborhood, withour losing any potential dependence structures, and 2) is applicable to both homogeneous and heterogeneous graph embedding, the latter of which is challenged by the diversity of node types. Furthermore, we provide theoretical guarantee for the representation capability of our method for general homogeneous and heterogeneous graphs. Empirical evaluation results on benchmark data sets show that our proposed PINE method outperforms the state-of-the-art approaches on producing node vectors for various learning tasks of both homogeneous and heterogeneous graphs.
Tasks	Community Detection, Graph Embedding, Node Classification
Published	2019-09-25
URL	https://arxiv.org/abs/1909.12903v1
PDF	https://arxiv.org/pdf/1909.12903v1.pdf
PWC	https://paperswithcode.com/paper/pine-universal-deep-embedding-for-graph-nodes
Repo
Framework

Knee Cartilage Segmentation Using Diffusion-Weighted MRI


Title	Knee Cartilage Segmentation Using Diffusion-Weighted MRI
Authors	Alejandra Duarte, Chaitra V. Hegde, Aakash Kaku, Sreyas Mohan, José G. Raya
Abstract	The integrity of articular cartilage is a crucial aspect in the early diagnosis of osteoarthritis (OA). Many novel MRI techniques have the potential to assess compositional changes of the cartilage extracellular matrix. Among these techniques, diffusion tensor imaging (DTI) of cartilage provides a simultaneous assessment of the two principal components of the solid matrix: collagen structure and proteoglycan concentration. DTI, as for any other compositional MRI technique, require a human expert to perform segmentation manually. The manual segmentation is error-prone and time-consuming ($\sim$ few hours per subject). We use an ensemble of modified U-Nets to automate this segmentation task. We benchmark our model against a human expert test-retest segmentation and conclude that our model is superior for Patellar and Tibial cartilage using dice score as the comparison metric. In the end, we do a perturbation analysis to understand the sensitivity of our model to the different components of our input. We also provide confidence maps for the predictions so that radiologists can tweak the model predictions as required. The model has been deployed in practice. In conclusion, cartilage segmentation on DW-MRI images with modified U-Nets achieves accuracy that outperforms the human segmenter. Code is available at https://github.com/aakashrkaku/knee-cartilage-segmentation
Tasks
Published	2019-12-04
URL	https://arxiv.org/abs/1912.01838v1
PDF	https://arxiv.org/pdf/1912.01838v1.pdf
PWC	https://paperswithcode.com/paper/knee-cartilage-segmentation-using-diffusion
Repo
Framework

Heterogeneous-Temporal Graph Convolutional Networks: Make the Community Detection Much Better


Title	Heterogeneous-Temporal Graph Convolutional Networks: Make the Community Detection Much Better
Authors	Yaping Zheng, Shiyi Chen, Xinni Zhang, Xiaofeng Zhang, Xiaofei Yang, Di Wang
Abstract	Community detection has long been an important yet challenging task to analyze complex networks with a focus on detecting topological structures of graph data. Essentially, real-world graph data contains various features, node and edge types which dynamically vary over time, and this invalidates most existing community detection approaches. To cope with these issues, this paper proposes the heterogeneous-temporal graph convolutional networks (HTGCN) to detect communities from hetergeneous and temporal graphs. Particularly, we first design a heterogeneous GCN component to acquire feature representations for each heterogeneous graph at each time step. Then, a residual compressed aggregation component is proposed to represent “dynamic” features for “varying” communities, which are then aggregated with “static” features extracted from current graph. Extensive experiments are evaluated on two real-world datasets, i.e., DBLP and IMDB. The promising results demonstrate that the proposed HTGCN is superior to both benchmark and the state-of-the-art approaches, e.g., GCN, GAT, GNN, LGNN, HAN and STAR, with respect to a number of evaluation criteria.
Tasks	Community Detection
Published	2019-09-23
URL	https://arxiv.org/abs/1909.10248v2
PDF	https://arxiv.org/pdf/1909.10248v2.pdf
PWC	https://paperswithcode.com/paper/190910248
Repo
Framework

Learning interpretable continuous-time models of latent stochastic dynamical systems


Title	Learning interpretable continuous-time models of latent stochastic dynamical systems
Authors	Lea Duncker, Gergo Bohner, Julien Boussard, Maneesh Sahani
Abstract	We develop an approach to learn an interpretable semi-parametric model of a latent continuous-time stochastic dynamical system, assuming noisy high-dimensional outputs sampled at uneven times. The dynamics are described by a nonlinear stochastic differential equation (SDE) driven by a Wiener process, with a drift evolution function drawn from a Gaussian process (GP) conditioned on a set of learnt fixed points and corresponding local Jacobian matrices. This form yields a flexible nonparametric model of the dynamics, with a representation corresponding directly to the interpretable portraits routinely employed in the study of nonlinear dynamical systems. The learning algorithm combines inference of continuous latent paths underlying observed data with a sparse variational description of the dynamical process. We demonstrate our approach on simulated data from different nonlinear dynamical systems.
Tasks
Published	2019-02-12
URL	http://arxiv.org/abs/1902.04420v1
PDF	http://arxiv.org/pdf/1902.04420v1.pdf
PWC	https://paperswithcode.com/paper/learning-interpretable-continuous-time-models
Repo
Framework

Non-destructive three-dimensional measurement of hand vein based on self-supervised network


Title	Non-destructive three-dimensional measurement of hand vein based on self-supervised network
Authors	Xiaoyu Chen, Qixin Wang, Jinzhou Ge, Yi Zhang, Jing Han
Abstract	At present, supervised stereo methods based on deep neural network have achieved impressive results. However, in some scenarios, accurate three-dimensional labels are inaccessible for supervised training. In this paper, a self-supervised network is proposed for binocular disparity matching (SDMNet), which computes dense disparity maps from stereo image pairs without disparity labels: In the self-supervised training, we match the stereo images densely to approximate the disparity maps and use them to warp the left and right images to estimate the right and left images; we build the loss function between estimated images and original images for self-supervised training, which adopts perceptual loss to help improve the quality of disparity maps in both detail and structure. Then, we use SDMNet to obtain disparities of hand vein. SDMNet has achieved excellent results on KITTI 2012, KITTI 2015, simulated vein dataset and real vein dataset, outperforming many state-of-the-art supervised matching methods.
Tasks
Published	2019-06-29
URL	https://arxiv.org/abs/1907.00215v1
PDF	https://arxiv.org/pdf/1907.00215v1.pdf
PWC	https://paperswithcode.com/paper/non-destructive-three-dimensional-measurement
Repo
Framework

Stereoscopic Dark Flash for Low-light Photography


Title	Stereoscopic Dark Flash for Low-light Photography
Authors	Jian Wang, Tianfan Xue, Jonathan T. Barron, Jiawen Chen
Abstract	In this work, we present a camera configuration for acquiring “stereoscopic dark flash” images: a simultaneous stereo pair in which one camera is a conventional RGB sensor, but the other camera is sensitive to near-infrared and near-ultraviolet instead of R and B. When paired with a “dark” flash (i.e., one having near-infrared and near-ultraviolet light, but no visible light) this camera allows us to capture the two images in a flash/no-flash image pair at the same time, all while not disturbing any human subjects or onlookers with a dazzling visible flash. We present a hardware prototype of this camera that approximates an idealized camera, and we present an imaging procedure that let us acquire dark flash stereo pairs that closely resemble those we would get from that idealized camera. We then present a technique for fusing these stereo pairs, first by performing registration and warping, and then by using recent advances in hyperspectral image fusion and deep learning to produce a final image. Because our camera configuration and our data acquisition process allow us to capture true low-noise long exposure RGB images alongside our dark flash stereo pairs, our learned model can be trained end-to-end to produce a fused image that retains the color and tone of a real RGB image while having the low-noise properties of a flash image.
Tasks
Published	2019-01-05
URL	http://arxiv.org/abs/1901.01370v2
PDF	http://arxiv.org/pdf/1901.01370v2.pdf
PWC	https://paperswithcode.com/paper/stereoscopic-dark-flash-for-low-light
Repo
Framework

A Learning based Branch and Bound for Maximum Common Subgraph Problems


Title	A Learning based Branch and Bound for Maximum Common Subgraph Problems
Authors	Yan-li Liu, Chu-min Li, Hua Jiang, Kun He
Abstract	Branch-and-bound (BnB) algorithms are widely used to solve combinatorial problems, and the performance crucially depends on its branching heuristic.In this work, we consider a typical problem of maximum common subgraph (MCS), and propose a branching heuristic inspired from reinforcement learning with a goal of reaching a tree leaf as early as possible to greatly reduce the search tree size.Extensive experiments show that our method is beneficial and outperforms current best BnB algorithm for the MCS.
Tasks
Published	2019-05-15
URL	https://arxiv.org/abs/1905.05840v2
PDF	https://arxiv.org/pdf/1905.05840v2.pdf
PWC	https://paperswithcode.com/paper/a-learning-based-branch-and-bound-for-maximum
Repo
Framework

tspDB: Time Series Predict DB


Title	tspDB: Time Series Predict DB
Authors	Anish Agarwal, Abdullah Alomar, Muhammad J. Amjad, Robert Lindland, Devavrat Shah
Abstract	In this work, we are motivated to make predictive functionality native to database (DB) systems, with a focus on time series data. We propose a system architecture, time series predict DB (tspDB), that enables predictive query functionality in any existing relational DB by building an additional prediction index for a time series of interest. Like standard DB indices, a prediction index must allow for fast data retrieval, but for entries that: (i) are for a future time step (i.e. forecasting); (ii) are missing/corrupted by noise (i.e. imputation). Such an index must satisfy: (i) statistical accuracy; (ii) high DB throughput; (iii) low predictive query latency; (iv) flexibility across DB/machines. Our hope is tspDB allows any analyst who can make a SQL query to make a predictive SQL query without loss of system performance, thereby increasing accessibility of machine learning. We build such a prediction index in PostgreSQL. it uses a recently developed prediction algorithm, which we alter to be incremental while maintaining its statistical accuracy. As an important algorithmic contribution, we develop a novel algorithm to estimate time-varying noise variance to enable uncertainty quantification. We argue it provides consistent estimation for a rich class of generating processes. Despite extensive literature, our variance estimation algorithm and associated analysis is first of its kind. For tspDB to function as a real-time system, we measure performance not only statistically but also through standard DB metrics such as latency/throughput. Statistically, the prediction index provides better accuracy compared to the state-of-art libraries. In terms of throughput, our index updates 2.83x faster than PostgreSQL bulk insert. Finally, predictive query latency with respect to standard SELECT queries is < 2.53x, < 6.09x for imputation/forecasting respectively (across DBs/machines)
Tasks	Imputation, Time Series
Published	2019-03-17
URL	https://arxiv.org/abs/1903.07097v3
PDF	https://arxiv.org/pdf/1903.07097v3.pdf
PWC	https://paperswithcode.com/paper/time-series-predict-db
Repo
Framework

Community Detection and Improved Detectability in Multiplex Networks


Title	Community Detection and Improved Detectability in Multiplex Networks
Authors	Yuming Huang, Ashkan Panahi, Hamid Krim, Liyi Dai
Abstract	We investigate the widely encountered problem of detecting communities in multiplex networks, such as social networks, with an unknown arbitrary heterogeneous structure. To improve detectability, we propose a generative model that leverages the multiplicity of a single community in multiple layers, with no prior assumption on the relation of communities among different layers. Our model relies on a novel idea of incorporating a large set of generic localized community label constraints across the layers, in conjunction with the celebrated Stochastic Block Model (SBM) in each layer. Accordingly, we build a probabilistic graphical model over the entire multiplex network by treating the constraints as Bayesian priors. We mathematically prove that these constraints/priors promote existence of identical communities across layers without introducing further correlation between individual communities. The constraints are further tailored to render a sparse graphical model and the numerically efficient Belief Propagation algorithm is subsequently employed. We further demonstrate by numerical experiments that in the presence of consistent communities between different layers, consistent communities are matched, and the detectability is improved over a single layer. We compare our model with a “correlated model” which exploits the prior knowledge of community correlation between layers. Similar detectability improvement is obtained under such a correlation, even though our model relies on much milder assumptions than the correlated model. Our model even shows a better detection performance over a certain correlation and signal to noise ratio (SNR) range. In the absence of community correlation, the correlation model naturally fails, while ours maintains its performance.
Tasks	Community Detection
Published	2019-09-23
URL	https://arxiv.org/abs/1909.10477v2
PDF	https://arxiv.org/pdf/1909.10477v2.pdf
PWC	https://paperswithcode.com/paper/community-detection-and-improved
Repo
Framework

Neural Gaussian Copula for Variational Autoencoder


Title	Neural Gaussian Copula for Variational Autoencoder
Authors	Prince Zizhuang Wang, William Yang Wang
Abstract	Variational language models seek to estimate the posterior of latent variables with an approximated variational posterior. The model often assumes the variational posterior to be factorized even when the true posterior is not. The learned variational posterior under this assumption does not capture the dependency relationships over latent variables. We argue that this would cause a typical training problem called posterior collapse observed in all other variational language models. We propose Gaussian Copula Variational Autoencoder (VAE) to avert this problem. Copula is widely used to model correlation and dependencies of high-dimensional random variables, and therefore it is helpful to maintain the dependency relationships that are lost in VAE. The empirical results show that by modeling the correlation of latent variables explicitly using a neural parametric copula, we can avert this training difficulty while getting competitive results among all other VAE approaches.
Tasks
Published	2019-09-09
URL	https://arxiv.org/abs/1909.03569v1
PDF	https://arxiv.org/pdf/1909.03569v1.pdf
PWC	https://paperswithcode.com/paper/neural-gaussian-copula-for-variational
Repo
Framework

Preterm infants’ limb-pose estimation from depth images using convolutional neural networks


Title	Preterm infants’ limb-pose estimation from depth images using convolutional neural networks
Authors	Sara Moccia, Lucia Migliorelli, Rocco Pietrini, Emanuele Frontoni
Abstract	Preterm infants’ limb-pose estimation is a crucial but challenging task, which may improve patients’ care and facilitate clinicians in infant’s movements monitoring. Work in the literature either provides approaches to whole-body segmentation and tracking, which, however, has poor clinical value, or retrieve a posteriori limb pose from limb segmentation, increasing computational costs and introducing inaccuracy sources. In this paper, we address the problem of limb-pose estimation under a different point of view. We proposed a 2D fully-convolutional neural network for roughly detecting limb joints and joint connections, followed by a regression convolutional neural network for accurate joint and joint-connection position estimation. Joints from the same limb are then connected with a maximum bipartite matching approach. Our analysis does not require any prior modeling of infants’ body structure, neither any manual interventions. For developing and testing the proposed approach, we built a dataset of four videos (video length = 90 s) recorded with a depth sensor in a neonatal intensive care unit (NICU) during the actual clinical practice, achieving median root mean square distance [pixels] of 10.790 (right arm), 10.542 (left arm), 8.294 (right leg), 11.270 (left leg) with respect to the ground-truth limb pose. The idea of estimating limb pose directly from depth images may represent a future paradigm for addressing the problem of preterm-infants’ movement monitoring and offer all possible support to clinicians in NICUs.
Tasks	Pose Estimation
Published	2019-07-26
URL	https://arxiv.org/abs/1907.12949v1
PDF	https://arxiv.org/pdf/1907.12949v1.pdf
PWC	https://paperswithcode.com/paper/preterm-infants-limb-pose-estimation-from
Repo
Framework

Recent Advances in Neural Question Generation


Title	Recent Advances in Neural Question Generation
Authors	Liangming Pan, Wenqiang Lei, Tat-Seng Chua, Min-Yen Kan
Abstract	Emerging research in Neural Question Generation (NQG) has started to integrate a larger variety of inputs, and generating questions requiring higher levels of cognition. These trends point to NQG as a bellwether for NLP, about how human intelligence embodies the skills of curiosity and integration. We present a comprehensive survey of neural question generation, examining the corpora, methodologies, and evaluation methods. From this, we elaborate on what we see as emerging on NQG’s trend: in terms of the learning paradigms, input modalities, and cognitive levels considered by NQG. We end by pointing out the potential directions ahead.
Tasks	Question Generation
Published	2019-05-22
URL	https://arxiv.org/abs/1905.08949v3
PDF	https://arxiv.org/pdf/1905.08949v3.pdf
PWC	https://paperswithcode.com/paper/recent-advances-in-neural-question-generation
Repo
Framework

Segmentation of Defective Skulls from CT Data for Tissue Modelling


Title	Segmentation of Defective Skulls from CT Data for Tissue Modelling
Authors	Oldřich Kodym, Michal Španěl, Adam Herout
Abstract	In this work we present a method of automatic segmentation of defective skulls for custom cranial implant design and 3D printing purposes. Since such tissue models are usually required in patient cases with complex anatomical defects and variety of external objects present in the acquired data, most deep learning-based approaches fall short because it is not possible to create a sufficient training dataset that would encompass the spectrum of all possible structures. Because CNN segmentation experiments in this application domain have been so far limited to simple patch-based CNN architectures, we first show how the usage of the encoder-decoder architecture can substantially improve the segmentation accuracy. Then, we show how the number of segmentation artifacts, which usually require manual corrections, can be further reduced by adding a boundary term to CNN training and by globally optimizing the segmentation with graph-cut. Finally, we show that using the proposed method, 3D segmentation accurate enough for clinical application can be achieved with 2D CNN architectures as well as their 3D counterparts.
Tasks
Published	2019-11-20
URL	https://arxiv.org/abs/1911.08805v1
PDF	https://arxiv.org/pdf/1911.08805v1.pdf
PWC	https://paperswithcode.com/paper/segmentation-of-defective-skulls-from-ct-data
Repo
Framework

Towards Self-similarity Consistency and Feature Discrimination for Unsupervised Domain Adaptation


Title	Towards Self-similarity Consistency and Feature Discrimination for Unsupervised Domain Adaptation
Authors	Chao Chen, Zhihang Fu, Zhihong Chen, Zhaowei Cheng, Xinyu Jin, Xian-Sheng Hua
Abstract	Recent advances in unsupervised domain adaptation mainly focus on learning shared representations by global distribution alignment without considering class information across domains. The neglect of class information, however, may lead to partial alignment (or even misalignment) and poor generalization performance. For comprehensive alignment, we argue that the similarities across different features in the source domain should be consistent with that of in the target domain. Based on this assumption, we propose a new domain discrepancy metric, i.e., Self-similarity Consistency (SSC), to enforce the feature structure being consistent across domains. The renowned correlation alignment (CORAL) is proven to be a special case, and a sub-optimal measure of our proposed SSC. Furthermore, we also propose to mitigate the side effect of the partial alignment and misalignment by incorporating the discriminative information of the deep representations. Specifically, an embarrassingly simple and effective feature norm constraint is exploited to enlarge the discrepancy of inter-class samples. It relieves the requirements of strict alignment when performing adaptation, therefore improving the adaptation performance significantly. Extensive experiments on visual domain adaptation tasks demonstrate the effectiveness of our proposed SSC metric and feature discrimination approach.
Tasks	Domain Adaptation, Unsupervised Domain Adaptation
Published	2019-04-13
URL	http://arxiv.org/abs/1904.06490v1
PDF	http://arxiv.org/pdf/1904.06490v1.pdf
PWC	https://paperswithcode.com/paper/towards-self-similarity-consistency-and
Repo
Framework