April 2, 2020

3215 words 16 mins read

Paper Group ANR 134

HAN-ECG: An Interpretable Atrial Fibrillation Detection Model Using Hierarchical Attention Networks. Learning word-referent mappings and concepts from raw inputs. Learning functions varying along an active subspace. Mirrored Autoencoders with Simplex Interpolation for Unsupervised Anomaly Detection. Deep connections between learning from limited la …

HAN-ECG: An Interpretable Atrial Fibrillation Detection Model Using Hierarchical Attention Networks


Title	HAN-ECG: An Interpretable Atrial Fibrillation Detection Model Using Hierarchical Attention Networks
Authors	Sajad Mousavi, Fatemeh Afghah, U. Rajendra Acharya
Abstract	Atrial fibrillation (AF) is one of the most prevalent cardiac arrhythmias that affects the lives of more than 3 million people in the U.S. and over 33 million people around the world and is associated with a five-fold increased risk of stroke and mortality. like other problems in healthcare domain, artificial intelligence (AI)-based algorithms have been used to reliably detect AF from patients’ physiological signals. The cardiologist level performance in detecting this arrhythmia is often achieved by deep learning-based methods, however, they suffer from the lack of interpretability. In other words, these approaches are unable to explain the reasons behind their decisions. The lack of interpretability is a common challenge toward a wide application of machine learning-based approaches in the healthcare which limits the trust of clinicians in such methods. To address this challenge, we propose HAN-ECG, an interpretable bidirectional-recurrent-neural-network-based approach for the AF detection task. The HAN-ECG employs three attention mechanism levels to provide a multi-resolution analysis of the patterns in ECG leading to AF. The first level, wave level, computes the wave weights, the second level, heartbeat level, calculates the heartbeat weights, and third level, window (i.e., multiple heartbeats) level, produces the window weights in triggering a class of interest. The detected patterns by this hierarchical attention model facilitate the interpretation of the neural network decision process in identifying the patterns in the signal which contributed the most to the final prediction. Experimental results on two AF databases demonstrate that our proposed model performs significantly better than the existing algorithms. Visualization of these attention layers illustrates that our model decides upon the important waves and heartbeats which are clinically meaningful in the detection task.
Tasks	Atrial Fibrillation Detection
Published	2020-02-12
URL	https://arxiv.org/abs/2002.05262v1
PDF	https://arxiv.org/pdf/2002.05262v1.pdf
PWC	https://paperswithcode.com/paper/han-ecg-an-interpretable-atrial-fibrillation
Repo
Framework

Learning word-referent mappings and concepts from raw inputs


Title	Learning word-referent mappings and concepts from raw inputs
Authors	Wai Keen Vong, Brenden M. Lake
Abstract	How do children learn correspondences between the language and the world from noisy, ambiguous, naturalistic input? One hypothesis is via cross-situational learning: tracking words and their possible referents across multiple situations allows learners to disambiguate correct word-referent mappings (Yu & Smith, 2007). However, previous models of cross-situational word learning operate on highly simplified representations, side-stepping two important aspects of the actual learning problem. First, how can word-referent mappings be learned from raw inputs such as images? Second, how can these learned mappings generalize to novel instances of a known word? In this paper, we present a neural network model trained from scratch via self-supervision that takes in raw images and words as inputs, and show that it can learn word-referent mappings from fully ambiguous scenes and utterances through cross-situational learning. In addition, the model generalizes to novel word instances, locates referents of words in a scene, and shows a preference for mutual exclusivity.
Tasks
Published	2020-03-12
URL	https://arxiv.org/abs/2003.05573v1
PDF	https://arxiv.org/pdf/2003.05573v1.pdf
PWC	https://paperswithcode.com/paper/learning-word-referent-mappings-and-concepts
Repo
Framework

Learning functions varying along an active subspace


Title	Learning functions varying along an active subspace
Authors	Hao Liu, Wenjing Liao
Abstract	Many functions of interest are in a high-dimensional space but exhibit low-dimensional structures. This paper studies regression of a $s$-H"{o}lder function $f$ in $\mathbb{R}^D$ which varies along an active subspace of dimension $d$ while $d\ll D$. A direct approximation of $f$ in $\mathbb{R}^D$ with an $\varepsilon$ accuracy requires the number of samples $n$ in the order of $\varepsilon^{-(2s+D)/s}$. In this paper, we modify the Generalized Contour Regression (GCR) algorithm to estimate the active subspace and use piecewise polynomials for function approximation. GCR is among the best estimators for the active subspace, but its sample complexity is an open question. Our modified GCR improves the efficiency over the original GCR and leads to an mean squared estimation error of $O(n^{-1})$ for the active subspace, when $n$ is sufficiently large. The mean squared regression error of $f$ is proved to be in the order of $\left(n/\log n\right)^{-\frac{2s}{2s+d}}$ where the exponent depends on the dimension of the active subspace $d$ instead of the ambient space $D$. This result demonstrates that GCR is effective in learning low-dimensional active subspaces. The convergence rate is validated through several numerical experiments.
Tasks
Published	2020-01-22
URL	https://arxiv.org/abs/2001.07883v2
PDF	https://arxiv.org/pdf/2001.07883v2.pdf
PWC	https://paperswithcode.com/paper/learning-functions-varying-along-an-active
Repo
Framework

Mirrored Autoencoders with Simplex Interpolation for Unsupervised Anomaly Detection


Title	Mirrored Autoencoders with Simplex Interpolation for Unsupervised Anomaly Detection
Authors	Y. Wu, Y. Balaji, B. Vinzamuri, S. Feizi
Abstract	Use of deep generative models for unsupervised anomaly detection has shown great promise partially owing to their ability to learn proper representations of complex input data distributions. Current methods, however, lack a strong latent representation of the data, thereby resulting in sub-optimal unsupervised anomaly detection results. In this work, we propose a novel representation learning technique using deep autoencoders to tackle the problem of unsupervised anomaly detection. Our approach replaces the $L_{p}$ reconstruction loss in the autoencoder optimization objective with a novel adversarial loss to enforce semantic-level reconstruction. In addition, we propose a novel simplex interpolation loss to improve the structure of the latent space representation in the autoencoder. Our technique improves the state-of-the-art unsupervised anomaly detection performance by a large margin on several image datasets including MNIST, fashion MNIST, CIFAR and Coil-100 as well as on several non-image datasets including KDD99, Arrhythmia and Thyroid. For example, On the CIFAR-10 dataset, using a standard leave-one-out evaluation protocol, our method achieves a substantial performance gain of 0.23 AUC points compared to the state-of-the-art.
Tasks	Anomaly Detection, Representation Learning, Unsupervised Anomaly Detection
Published	2020-03-24
URL	https://arxiv.org/abs/2003.10713v1
PDF	https://arxiv.org/pdf/2003.10713v1.pdf
PWC	https://paperswithcode.com/paper/mirrored-autoencoders-with-simplex
Repo
Framework

Deep connections between learning from limited labels & physical parameter estimation – inspiration for regularization


Title	Deep connections between learning from limited labels & physical parameter estimation – inspiration for regularization
Authors	Bas Peters
Abstract	Recently established equivalences between differential equations and the structure of neural networks enabled some interpretation of training of a neural network as partial-differential-equation (PDE) constrained optimization. We add to the previously established connections, explicit regularization that is particularly beneficial in the case of single large-scale examples with partial annotation. We show that explicit regularization of model parameters in PDE constrained optimization translates to regularization of the network output. Examination of the structure of the corresponding Lagrangian and backpropagation algorithm do not reveal additional computational challenges. A hyperspectral imaging example shows that minimum prior information together with cross-validation for optimal regularization parameters boosts the segmentation accuracy.
Tasks
Published	2020-03-17
URL	https://arxiv.org/abs/2003.07908v1
PDF	https://arxiv.org/pdf/2003.07908v1.pdf
PWC	https://paperswithcode.com/paper/deep-connections-between-learning-from
Repo
Framework

BANet: Bidirectional Aggregation Network with Occlusion Handling for Panoptic Segmentation


Title	BANet: Bidirectional Aggregation Network with Occlusion Handling for Panoptic Segmentation
Authors	Yifeng Chen, Guangchen Lin, Songyuan Li, Bourahla Omar, Yiming Wu, Fangfang Wang, Junyi Feng, Mingliang Xu, Xi Li
Abstract	Panoptic segmentation aims to perform instance segmentation for foreground instances and semantic segmentation for background stuff simultaneously. The typical top-down pipeline concentrates on two key issues: 1) how to effectively model the intrinsic interaction between semantic segmentation and instance segmentation, and 2) how to properly handle occlusion for panoptic segmentation. Intuitively, the complementarity between semantic segmentation and instance segmentation can be leveraged to improve the performance. Besides, we notice that using detection/mask scores is insufficient for resolving the occlusion problem. Motivated by these observations, we propose a novel deep panoptic segmentation scheme based on a bidirectional learning pipeline. Moreover, we introduce a plug-and-play occlusion handling algorithm to deal with the occlusion between different object instances. The experimental results on COCO panoptic benchmark validate the effectiveness of our proposed method. Codes will be released soon at https://github.com/Mooonside/BANet.
Tasks	Instance Segmentation, Panoptic Segmentation, Semantic Segmentation
Published	2020-03-31
URL	https://arxiv.org/abs/2003.14031v1
PDF	https://arxiv.org/pdf/2003.14031v1.pdf
PWC	https://paperswithcode.com/paper/banet-bidirectional-aggregation-network-with
Repo
Framework

Federated Learning for Task and Resource Allocation in Wireless High Altitude Balloon Networks


Title	Federated Learning for Task and Resource Allocation in Wireless High Altitude Balloon Networks
Authors	Sihua Wang, Mingzhe Chen, Changchuan Yin, Walid Saad, Choong Seon Hong, Shuguang Cui, H. Vincent Poor
Abstract	In this paper, the problem of minimizing energy and time consumption for task computation and transmission is studied in a mobile edge computing (MEC)-enabled balloon network. In the considered network, each user needs to process a computational task in each time instant, where high-altitude balloons (HABs), acting as flying wireless base stations, can use their powerful computational abilities to process the tasks offloaded from their associated users. Since the data size of each user’s computational task varies over time, the HABs must dynamically adjust the user association, service sequence, and task partition scheme to meet the users’ needs. This problem is posed as an optimization problem whose goal is to minimize the energy and time consumption for task computing and transmission by adjusting the user association, service sequence, and task allocation scheme. To solve this problem, a support vector machine (SVM)-based federated learning (FL) algorithm is proposed to determine the user association proactively. The proposed SVM-based FL method enables each HAB to cooperatively build an SVM model that can determine all user associations without any transmissions of either user historical associations or computational tasks to other HABs. Given the prediction of the optimal user association, the service sequence and task allocation of each user can be optimized so as to minimize the weighted sum of the energy and time consumption. Simulations with real data of city cellular traffic from the OMNILab at Shanghai Jiao Tong University show that the proposed algorithm can reduce the weighted sum of the energy and time consumption of all users by up to 16.1% compared to a conventional centralized method.
Tasks
Published	2020-03-19
URL	https://arxiv.org/abs/2003.09375v1
PDF	https://arxiv.org/pdf/2003.09375v1.pdf
PWC	https://paperswithcode.com/paper/federated-learning-for-task-and-resource
Repo
Framework

Online Passive-Aggressive Total-Error-Rate Minimization


Title	Online Passive-Aggressive Total-Error-Rate Minimization
Authors	Se-In Jang
Abstract	We provide a new online learning algorithm which utilizes online passive-aggressive learning (PA) and total-error-rate minimization (TER) for binary classification. The PA learning establishes not only large margin training but also the capacity to handle non-separable data. The TER learning on the other hand minimizes an approximated classification error based objective function. We propose an online PATER algorithm which combines those useful properties. In addition, we also present a weighted PATER algorithm to improve the ability to cope with data imbalance problems. Experimental results demonstrate that the proposed PATER algorithms achieves better performances in terms of efficiency and effectiveness than the existing state-of-the-art online learning algorithms in real-world data sets.
Tasks
Published	2020-02-05
URL	https://arxiv.org/abs/2002.01771v1
PDF	https://arxiv.org/pdf/2002.01771v1.pdf
PWC	https://paperswithcode.com/paper/online-passive-aggressive-total-error-rate
Repo
Framework

Knowledge representation and update in hierarchies of graphs


Title	Knowledge representation and update in hierarchies of graphs
Authors	Russ Harmer, Eugenia Oshurko
Abstract	A mathematical theory is presented for the representation of knowledge in the form of a directed acyclic hierarchy of objects in a category where all paths between any given pair of objects are required to be equal. The conditions under which knowledge update, in the form of the sesqui-pushout rewriting of an object in a hierarchy, can be propagated to the rest of the hierarchy, in order to maintain all required path equalities, are analysed: some rewrites must be propagated forwards, in the direction of the arrows, while others must be propagated backwards, against the direction of the arrows, and, depending on the precise form of the hierarchy, certain composability conditions may also be necessary. The implementation of this theory, in the ReGraph Python library for (simple) directed graphs with attributes on nodes and edges, is then discussed in the context of two significant use cases.
Tasks
Published	2020-02-05
URL	https://arxiv.org/abs/2002.01766v1
PDF	https://arxiv.org/pdf/2002.01766v1.pdf
PWC	https://paperswithcode.com/paper/knowledge-representation-and-update-in
Repo
Framework

FFusionCGAN: An end-to-end fusion method for few-focus images using conditional GAN in cytopathological digital slides


Title	FFusionCGAN: An end-to-end fusion method for few-focus images using conditional GAN in cytopathological digital slides
Authors	Xiebo Geng, Sibo Liua, Wei Han, Xu Li, Jiabo Ma, Jingya Yu, Xiuli Liu, Sahoqun Zeng, Li Chen, Shenghua Cheng
Abstract	Multi-focus image fusion technologies compress different focus depth images into an image in which most objects are in focus. However, although existing image fusion techniques, including traditional algorithms and deep learning-based algorithms, can generate high-quality fused images, they need multiple images with different focus depths in the same field of view. This criterion may not be met in some cases where time efficiency is required or the hardware is insufficient. The problem is especially prominent in large-size whole slide images. This paper focused on the multi-focus image fusion of cytopathological digital slide images, and proposed a novel method for generating fused images from single-focus or few-focus images based on conditional generative adversarial network (GAN). Through the adversarial learning of the generator and discriminator, the method is capable of generating fused images with clear textures and large depth of field. Combined with the characteristics of cytopathological images, this paper designs a new generator architecture combining U-Net and DenseBlock, which can effectively improve the network’s receptive field and comprehensively encode image features. Meanwhile, this paper develops a semantic segmentation network that identifies the blurred regions in cytopathological images. By integrating the network into the generative model, the quality of the generated fused images is effectively improved. Our method can generate fused images from only single-focus or few-focus images, thereby avoiding the problem of collecting multiple images of different focus depths with increased time and hardware costs. Furthermore, our model is designed to learn the direct mapping of input source images to fused images without the need to manually design complex activity level measurements and fusion rules as in traditional methods.
Tasks	Semantic Segmentation
Published	2020-01-03
URL	https://arxiv.org/abs/2001.00692v1
PDF	https://arxiv.org/pdf/2001.00692v1.pdf
PWC	https://paperswithcode.com/paper/ffusioncgan-an-end-to-end-fusion-method-for
Repo
Framework

Intelligent Bandwidth Allocation for Latency Management in NG-EPON using Reinforcement Learning Methods


Title	Intelligent Bandwidth Allocation for Latency Management in NG-EPON using Reinforcement Learning Methods
Authors	Qi Zhou, Jingjie Zhu, Junwen Zhang, Zhensheng Jia, Bernardo Huberman, Gee-Kung Chang
Abstract	A novel intelligent bandwidth allocation scheme in NG-EPON using reinforcement learning is proposed and demonstrated for latency management. We verify the capability of the proposed scheme under both fixed and dynamic traffic loads scenarios to achieve <1ms average latency. The RL agent demonstrates an efficient intelligent mechanism to manage the latency, which provides a promising IBA solution for the next-generation access network.
Tasks
Published	2020-01-21
URL	https://arxiv.org/abs/2001.07698v1
PDF	https://arxiv.org/pdf/2001.07698v1.pdf
PWC	https://paperswithcode.com/paper/intelligent-bandwidth-allocation-for-latency
Repo
Framework

Physics-Guided Deep Neural Networks for PowerFlow Analysis


Title	Physics-Guided Deep Neural Networks for PowerFlow Analysis
Authors	Xinyue Hu, Haoji Hu, Saurabh Verma, Zhi-Li Zhang
Abstract	Solving power flow (PF) equations is the basis of power flow analysis, which is important in determining the best operation of existing systems, performing security analysis, etc. However, PF equations can be out-of-date or even unavailable due to system dynamics and uncertainties, making traditional numerical approaches infeasible. To address these concerns, researchers have proposed data-driven approaches to solve the PF problem by learning the mapping rules from historical system operation data. Nevertheless, prior data-driven approaches suffer from poor performance and generalizability, due to overly simplified assumptions of the PF problem or ignorance of physical laws governing power systems. In this paper, we propose a physics-guided neural network to solve the PF problem, with an auxiliary task to rebuild the PF model. By encoding different granularity of Kirchhoff’s laws and system topology into the rebuilt PF model, our neural-network based PF solver is regularized by the auxiliary task and constrained by the physical laws. The simulation results show that our physics-guided neural network methods achieve better performance and generalizability compared to existing unconstrained data-driven approaches. Furthermore, we demonstrate that the weight matrices of our physics-guided neural networks embody power system physics by showing their similarities with the bus admittance matrices.
Tasks
Published	2020-01-31
URL	https://arxiv.org/abs/2002.00097v1
PDF	https://arxiv.org/pdf/2002.00097v1.pdf
PWC	https://paperswithcode.com/paper/physics-guided-deep-neural-networks-for
Repo
Framework

Mobility Inference on Long-Tailed Sparse Trajectory


Title	Mobility Inference on Long-Tailed Sparse Trajectory
Authors	Lei Shi
Abstract	Analyzing the urban trajectory in cities has become an important topic in data mining. How can we model the human mobility consisting of stay and travel from the raw trajectory data? How can we infer such a mobility model from the single trajectory information? How can we further generalize the mobility inference to accommodate the real-world trajectory data that is sparsely sampled over time? In this paper, based on formal and rigid definitions of the stay/travel mobility, we propose a single trajectory inference algorithm that utilizes a generic long-tailed sparsity pattern in the large-scale trajectory data. The algorithm guarantees a 100% precision in the stay/travel inference with a provable lower-bound in the recall. Furthermore, we introduce an encoder-decoder learning architecture that admits multiple trajectories as inputs. The architecture is optimized for the mobility inference problem through customized embedding and learning mechanism. Evaluations with three trajectory data sets of 40 million urban users validate the performance guarantees of the proposed inference algorithm and demonstrate the superiority of our deep learning model, in comparison to well-known sequence learning methods. On extremely sparse trajectories, the deep learning model achieves a 2$\times$ overall accuracy improvement from the single trajectory inference algorithm, through proven scalability and generalizability to large-scale versatile training data.
Tasks
Published	2020-01-21
URL	https://arxiv.org/abs/2001.07636v1
PDF	https://arxiv.org/pdf/2001.07636v1.pdf
PWC	https://paperswithcode.com/paper/mobility-inference-on-long-tailed-sparse
Repo
Framework

Optimal Image Smoothing and Its Applications in Anomaly Detection in Remote Sensing


Title	Optimal Image Smoothing and Its Applications in Anomaly Detection in Remote Sensing
Authors	M. Kiani
Abstract	This paper is focused on deriving an optimal image smoother. The optimization is done through the minimization of the norm of the Laplace operator in the image coordinate system. Discretizing the Laplace operator and using the method of Euler-Lagrange result in a weighted average scheme for the optimal smoother. Satellite imagery can be smoothed by this optimal smoother. It is also very fast and can be used for detecting the anomalies in the image. A real anomaly detecting problem is considered for the Qom region in Iran. Satellite image in different bands are smoothed. Comparing the smoothed and original images in different bands, the maps of anomalies are presented. Comparison between the derived method and the existing methods reveals that it is more efficient in detecting anomalies in the region.
Tasks	Anomaly Detection
Published	2020-03-17
URL	https://arxiv.org/abs/2003.08210v1
PDF	https://arxiv.org/pdf/2003.08210v1.pdf
PWC	https://paperswithcode.com/paper/optimal-image-smoothing-and-its-applications
Repo
Framework

Edge Preserving CNN SAR Despeckling Algorithm


Title	Edge Preserving CNN SAR Despeckling Algorithm
Authors	Sergio Vitale, Giampaolo Ferraioli, Vito pascazio
Abstract	SAR despeckling is a key tool for Earth Observation. Interpretation of SAR images are impaired by speckle, a multiplicative noise related to interference of backscattering from the illuminated scene towards the sensor. Reducing the noise is a crucial task for the understanding of the scene. Based on the results of our previous solution KL-DNN, in this work we define a new cost function for training a convolutional neural network for despeckling. The aim is to control the edge preservation and to better filter manmade structures and urban areas that are very challenging for KL-DNN. The results show a very good improvement on the not homogeneous areas keeping the good results in the homogeneous ones. Result on both simulated and real data are shown in the paper.
Tasks
Published	2020-01-14
URL	https://arxiv.org/abs/2001.04716v2
PDF	https://arxiv.org/pdf/2001.04716v2.pdf
PWC	https://paperswithcode.com/paper/edge-preserving-cnn-sar-despeckling-algorithm
Repo
Framework